diff --git a/baselines PPO.ipynb b/baselines PPO.ipynb index 46286c4..0443920 100644 --- a/baselines PPO.ipynb +++ b/baselines PPO.ipynb @@ -5,8 +5,8 @@ "execution_count": 1, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.251965Z", - "start_time": "2017-07-23T18:09:10.587905+08:00" + "end_time": "2017-07-23T10:19:05.277167Z", + "start_time": "2017-07-23T18:19:04.545650+08:00" } }, "outputs": [ @@ -50,8 +50,8 @@ "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.269736Z", - "start_time": "2017-07-23T18:09:11.253715+08:00" + "end_time": "2017-07-23T10:19:05.294255Z", + "start_time": "2017-07-23T18:19:05.278788+08:00" }, "collapsed": true }, @@ -68,8 +68,8 @@ "execution_count": 3, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.284126Z", - "start_time": "2017-07-23T18:09:11.271919+08:00" + "end_time": "2017-07-23T10:19:05.309090Z", + "start_time": "2017-07-23T18:19:05.295668+08:00" }, "collapsed": true }, @@ -83,8 +83,8 @@ "execution_count": 4, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.445252Z", - "start_time": "2017-07-23T18:09:11.285854+08:00" + "end_time": "2017-07-23T10:19:05.463111Z", + "start_time": "2017-07-23T18:19:05.310829+08:00" } }, "outputs": [], @@ -103,8 +103,8 @@ "execution_count": 5, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.466415Z", - "start_time": "2017-07-23T18:09:11.448177+08:00" + "end_time": "2017-07-23T10:19:05.480928Z", + "start_time": "2017-07-23T18:19:05.464967+08:00" }, "collapsed": true }, @@ -128,8 +128,8 @@ "execution_count": 6, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:11.617740Z", - "start_time": "2017-07-23T18:09:11.468059+08:00" + "end_time": "2017-07-23T10:19:05.601246Z", + "start_time": "2017-07-23T18:19:05.482642+08:00" } }, "outputs": [], @@ -159,8 +159,8 @@ "execution_count": 7, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:12.765737Z", - "start_time": "2017-07-23T18:09:11.620218+08:00" + "end_time": "2017-07-23T10:19:06.520542Z", + "start_time": "2017-07-23T18:19:05.602960+08:00" }, "collapsed": true }, @@ -245,8 +245,8 @@ "execution_count": 8, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:12.904604Z", - "start_time": "2017-07-23T18:09:12.767548+08:00" + "end_time": "2017-07-23T10:19:06.630212Z", + "start_time": "2017-07-23T18:19:06.522316+08:00" }, "collapsed": true }, @@ -323,8 +323,8 @@ "execution_count": 9, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:12.941241Z", - "start_time": "2017-07-23T18:09:12.909883+08:00" + "end_time": "2017-07-23T10:19:06.662265Z", + "start_time": "2017-07-23T18:19:06.632383+08:00" } }, "outputs": [ @@ -332,7 +332,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "Logging to /tmp/openai-2017-07-23-18-09-12-937124\n" + "Logging to /tmp/openai-2017-07-23-18-19-06-657524\n" ] } ], @@ -358,8 +358,8 @@ "execution_count": 10, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:12.963477Z", - "start_time": "2017-07-23T18:09:12.943064+08:00" + "end_time": "2017-07-23T10:19:06.684183Z", + "start_time": "2017-07-23T18:19:06.664617+08:00" }, "collapsed": true }, @@ -373,8 +373,8 @@ "execution_count": 11, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:12.985759Z", - "start_time": "2017-07-23T18:09:12.965000+08:00" + "end_time": "2017-07-23T10:19:06.705374Z", + "start_time": "2017-07-23T18:19:06.686530+08:00" }, "collapsed": true }, @@ -392,8 +392,8 @@ "execution_count": 12, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:13.658564Z", - "start_time": "2017-07-23T18:09:12.987480+08:00" + "end_time": "2017-07-23T10:19:07.233152Z", + "start_time": "2017-07-23T18:19:06.707196+08:00" } }, "outputs": [ @@ -409,7 +409,7 @@ "output_type": "stream", "text": [ "WARNING:tensorflow:VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n", - "[2017-07-23 18:09:13,597] VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n" + "[2017-07-23 18:19:07,176] VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n" ] }, { @@ -424,7 +424,7 @@ "output_type": "stream", "text": [ "WARNING:tensorflow:VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n", - "[2017-07-23 18:09:13,599] VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n" + "[2017-07-23 18:19:07,179] VARIABLES collection name is deprecated, please use GLOBAL_VARIABLES instead; VARIABLES will be removed after 2017-03-02.\n" ] } ], @@ -512,8 +512,8 @@ "execution_count": 13, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:09:13.692052Z", - "start_time": "2017-07-23T18:09:13.660699+08:00" + "end_time": "2017-07-23T10:19:07.254158Z", + "start_time": "2017-07-23T18:19:07.235136+08:00" }, "collapsed": true }, @@ -527,8 +527,8 @@ "execution_count": 14, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:10:17.287802Z", - "start_time": "2017-07-23T18:09:13.694505+08:00" + "end_time": "2017-07-23T13:16:32.444698Z", + "start_time": "2017-07-23T18:19:07.255881+08:00" } }, "outputs": [ @@ -536,7 +536,6 @@ "name": "stdout", "output_type": "stream", "text": [ - "********** Iteration 0 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00949 |\n", "| loss_pol_entpen | -0.0856 |\n", @@ -549,9 +548,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 0 |\n", "| TimestepsSoFar | 0 |\n", - "| TimeElapsed | 1.69 |\n", - "------------------------------\n", - "********** Iteration 1 ************\n" + "| TimeElapsed | 1.65 |\n", + "------------------------------\n" ] }, { @@ -580,9 +578,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 0 |\n", "| TimestepsSoFar | 0 |\n", - "| TimeElapsed | 3.19 |\n", + "| TimeElapsed | 3.15 |\n", "------------------------------\n", - "********** Iteration 2 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00613 |\n", "| loss_pol_entpen | -0.0859 |\n", @@ -595,9 +592,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 0 |\n", "| TimestepsSoFar | 0 |\n", - "| TimeElapsed | 4.57 |\n", + "| TimeElapsed | 4.72 |\n", "------------------------------\n", - "********** Iteration 3 ************\n", "------------------------------\n", "| loss_pol_surr | -0.015 |\n", "| loss_pol_entpen | -0.0861 |\n", @@ -610,9 +606,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 0 |\n", "| TimestepsSoFar | 0 |\n", - "| TimeElapsed | 5.93 |\n", + "| TimeElapsed | 6.3 |\n", "------------------------------\n", - "********** Iteration 4 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00715 |\n", "| loss_pol_entpen | -0.0865 |\n", @@ -625,15 +620,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 0 |\n", "| TimestepsSoFar | 0 |\n", - "| TimeElapsed | 7.32 |\n", + "| TimeElapsed | 7.96 |\n", "------------------------------\n", - "********** Iteration 5 ************\n", - "********** Iteration 6 ************\n", - "********** Iteration 7 ************\n", - "********** Iteration 8 ************\n", - "********** Iteration 9 ************\n", - "********** Iteration 10 ************\n", - "********** Iteration 11 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00861 |\n", "| loss_pol_entpen | -0.0867 |\n", @@ -646,9 +634,8 @@ "| EpThisIter | 1 |\n", "| EpisodesSoFar | 2 |\n", "| TimestepsSoFar | 2.88e+03 |\n", - "| TimeElapsed | 17.5 |\n", + "| TimeElapsed | 19.1 |\n", "------------------------------\n", - "********** Iteration 12 ************\n", "------------------------------\n", "| loss_pol_surr | -0.0144 |\n", "| loss_pol_entpen | -0.0869 |\n", @@ -661,9 +648,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 2 |\n", "| TimestepsSoFar | 2.88e+03 |\n", - "| TimeElapsed | 19 |\n", + "| TimeElapsed | 20.8 |\n", "------------------------------\n", - "********** Iteration 13 ************\n", "------------------------------\n", "| loss_pol_surr | -0.0104 |\n", "| loss_pol_entpen | -0.0875 |\n", @@ -676,9 +662,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 2 |\n", "| TimestepsSoFar | 2.88e+03 |\n", - "| TimeElapsed | 20.6 |\n", + "| TimeElapsed | 22.5 |\n", "------------------------------\n", - "********** Iteration 14 ************\n", "------------------------------\n", "| loss_pol_surr | -0.011 |\n", "| loss_pol_entpen | -0.0878 |\n", @@ -691,9 +676,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 2 |\n", "| TimestepsSoFar | 2.88e+03 |\n", - "| TimeElapsed | 22.4 |\n", + "| TimeElapsed | 24.1 |\n", "------------------------------\n", - "********** Iteration 15 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00717 |\n", "| loss_pol_entpen | -0.0878 |\n", @@ -706,15 +690,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 2 |\n", "| TimestepsSoFar | 2.88e+03 |\n", - "| TimeElapsed | 23.8 |\n", + "| TimeElapsed | 25.6 |\n", "------------------------------\n", - "********** Iteration 16 ************\n", - "********** Iteration 17 ************\n", - "********** Iteration 18 ************\n", - "********** Iteration 19 ************\n", - "********** Iteration 20 ************\n", - "********** Iteration 21 ************\n", - "********** Iteration 22 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00539 |\n", "| loss_pol_entpen | -0.0891 |\n", @@ -727,9 +704,8 @@ "| EpThisIter | 1 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 34.7 |\n", + "| TimeElapsed | 37.1 |\n", "------------------------------\n", - "********** Iteration 23 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00551 |\n", "| loss_pol_entpen | -0.0891 |\n", @@ -742,9 +718,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 36.4 |\n", + "| TimeElapsed | 38.5 |\n", "------------------------------\n", - "********** Iteration 24 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00499 |\n", "| loss_pol_entpen | -0.089 |\n", @@ -757,9 +732,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 38.2 |\n", + "| TimeElapsed | 39.8 |\n", "------------------------------\n", - "********** Iteration 25 ************\n", "------------------------------\n", "| loss_pol_surr | -0.0121 |\n", "| loss_pol_entpen | -0.0891 |\n", @@ -772,9 +746,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 39.8 |\n", + "| TimeElapsed | 41.2 |\n", "------------------------------\n", - "********** Iteration 26 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00409 |\n", "| loss_pol_entpen | -0.0891 |\n", @@ -787,9 +760,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 41.3 |\n", + "| TimeElapsed | 42.6 |\n", "------------------------------\n", - "********** Iteration 27 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00851 |\n", "| loss_pol_entpen | -0.0892 |\n", @@ -802,14 +774,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 4 |\n", "| TimestepsSoFar | 5.76e+03 |\n", - "| TimeElapsed | 42.7 |\n", + "| TimeElapsed | 44 |\n", "------------------------------\n", - "********** Iteration 28 ************\n", - "********** Iteration 29 ************\n", - "********** Iteration 30 ************\n", - "********** Iteration 31 ************\n", - "********** Iteration 32 ************\n", - "********** Iteration 33 ************\n", "------------------------------\n", "| loss_pol_surr | -0.0106 |\n", "| loss_pol_entpen | -0.0909 |\n", @@ -822,9 +788,8 @@ "| EpThisIter | 1 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 52 |\n", + "| TimeElapsed | 52.2 |\n", "------------------------------\n", - "********** Iteration 34 ************\n", "-------------------------------\n", "| loss_pol_surr | -0.00551 |\n", "| loss_pol_entpen | -0.0913 |\n", @@ -837,15 +802,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 53.7 |\n", - "-------------------------------\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "********** Iteration 35 ************\n", + "| TimeElapsed | 53.6 |\n", + "-------------------------------\n", "------------------------------\n", "| loss_pol_surr | -0.00297 |\n", "| loss_pol_entpen | -0.0915 |\n", @@ -858,9 +816,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 55.2 |\n", + "| TimeElapsed | 54.9 |\n", "------------------------------\n", - "********** Iteration 36 ************\n", "------------------------------\n", "| loss_pol_surr | -0.0122 |\n", "| loss_pol_entpen | -0.0923 |\n", @@ -873,9 +830,14 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 56.6 |\n", - "------------------------------\n", - "********** Iteration 37 ************\n", + "| TimeElapsed | 56.3 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ "------------------------------\n", "| loss_pol_surr | -0.00597 |\n", "| loss_pol_entpen | -0.0928 |\n", @@ -888,9 +850,8 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 58 |\n", + "| TimeElapsed | 57.6 |\n", "------------------------------\n", - "********** Iteration 38 ************\n", "------------------------------\n", "| loss_pol_surr | -0.00415 |\n", "| loss_pol_entpen | -0.0929 |\n", @@ -903,30 +864,56884 @@ "| EpThisIter | 0 |\n", "| EpisodesSoFar | 6 |\n", "| TimestepsSoFar | 8.64e+03 |\n", - "| TimeElapsed | 59.4 |\n", + "| TimeElapsed | 59.1 |\n", "------------------------------\n", - "********** Iteration 39 ************\n", - "********** Iteration 40 ************\n", - "********** Iteration 41 ************\n" + "------------------------------\n", + "| loss_pol_surr | -0.00882 |\n", + "| loss_pol_entpen | -0.0946 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000943 |\n", + "| loss_ent | 9.46 |\n", + "| ev_tdlam_before | -0.00465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 67.4 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.0947 |\n", + "| loss_vf_loss | 3.9e-11 |\n", + "| loss_kl | 0.000631 |\n", + "| loss_ent | 9.47 |\n", + "| ev_tdlam_before | 0.000949 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 68.7 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.0946 |\n", + "| loss_vf_loss | 9.58e-11 |\n", + "| loss_kl | 0.00038 |\n", + "| loss_ent | 9.46 |\n", + "| ev_tdlam_before | 0.00146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 70.1 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00649 |\n", + "| loss_pol_entpen | -0.0944 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000467 |\n", + "| loss_ent | 9.44 |\n", + "| ev_tdlam_before | 0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 71.4 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00584 |\n", + "| loss_pol_entpen | -0.0943 |\n", + "| loss_vf_loss | 8.18e-11 |\n", + "| loss_kl | 0.000724 |\n", + "| loss_ent | 9.43 |\n", + "| ev_tdlam_before | -0.0094 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 72.8 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00771 |\n", + "| loss_pol_entpen | -0.0944 |\n", + "| loss_vf_loss | 5.35e-11 |\n", + "| loss_kl | 0.00079 |\n", + "| loss_ent | 9.44 |\n", + "| ev_tdlam_before | 0.000436 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000379 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 8 |\n", + "| TimestepsSoFar | 1.15e+04 |\n", + "| TimeElapsed | 74.2 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00666 |\n", + "| loss_pol_entpen | -0.0947 |\n", + "| loss_vf_loss | 7.22e-11 |\n", + "| loss_kl | 0.00058 |\n", + "| loss_ent | 9.47 |\n", + "| ev_tdlam_before | -0.00141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00036 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 10 |\n", + "| TimestepsSoFar | 1.44e+04 |\n", + "| TimeElapsed | 83.7 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00701 |\n", + "| loss_pol_entpen | -0.0948 |\n", + "| loss_vf_loss | 6.01e-11 |\n", + "| loss_kl | 0.000751 |\n", + "| loss_ent | 9.48 |\n", + "| ev_tdlam_before | 0.000148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00036 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 10 |\n", + "| TimestepsSoFar | 1.44e+04 |\n", + "| TimeElapsed | 85 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00754 |\n", + "| loss_pol_entpen | -0.0948 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000692 |\n", + "| loss_ent | 9.48 |\n", + "| ev_tdlam_before | 0.00453 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00036 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 10 |\n", + "| TimestepsSoFar | 1.44e+04 |\n", + "| TimeElapsed | 86.4 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0113 |\n", + "| loss_pol_entpen | -0.0948 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.00123 |\n", + "| loss_ent | 9.48 |\n", + "| ev_tdlam_before | 0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00036 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 10 |\n", + "| TimestepsSoFar | 1.44e+04 |\n", + "| TimeElapsed | 87.8 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0078 |\n", + "| loss_pol_entpen | -0.0948 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000951 |\n", + "| loss_ent | 9.48 |\n", + "| ev_tdlam_before | 0.000184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00036 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 10 |\n", + "| TimestepsSoFar | 1.44e+04 |\n", + "| TimeElapsed | 89.1 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00497 |\n", + "| loss_pol_entpen | -0.0942 |\n", + "| loss_vf_loss | 6.18e-11 |\n", + "| loss_kl | 0.000912 |\n", + "| loss_ent | 9.42 |\n", + "| ev_tdlam_before | -0.000165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 98.6 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.019 |\n", + "| loss_pol_entpen | -0.0948 |\n", + "| loss_vf_loss | 5.48e-10 |\n", + "| loss_kl | 0.0022 |\n", + "| loss_ent | 9.48 |\n", + "| ev_tdlam_before | -0.537 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 100 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00409 |\n", + "| loss_pol_entpen | -0.0952 |\n", + "| loss_vf_loss | 1.18e-08 |\n", + "| loss_kl | 0.000798 |\n", + "| loss_ent | 9.52 |\n", + "| ev_tdlam_before | -0.00337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 101 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00523 |\n", + "| loss_pol_entpen | -0.0952 |\n", + "| loss_vf_loss | 4.23e-08 |\n", + "| loss_kl | 0.000541 |\n", + "| loss_ent | 9.52 |\n", + "| ev_tdlam_before | -0.733 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 103 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00851 |\n", + "| loss_pol_entpen | -0.0955 |\n", + "| loss_vf_loss | 8.07e-09 |\n", + "| loss_kl | 0.000674 |\n", + "| loss_ent | 9.55 |\n", + "| ev_tdlam_before | -2.51 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 104 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00961 |\n", + "| loss_pol_entpen | -0.0959 |\n", + "| loss_vf_loss | 5.58e-09 |\n", + "| loss_kl | 0.00144 |\n", + "| loss_ent | 9.59 |\n", + "| ev_tdlam_before | -0.647 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 12 |\n", + "| TimestepsSoFar | 1.73e+04 |\n", + "| TimeElapsed | 105 |\n", + "------------------------------\n" ] }, { - "ename": "KeyboardInterrupt", - "evalue": "", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0mlogger\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"********** Iteration %i ************\"\u001b[0m\u001b[0;34m%\u001b[0m\u001b[0miters_so_far\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 22\u001b[0;31m \u001b[0mseg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mseg_gen\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__next__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 23\u001b[0m \u001b[0mpposgd_simple\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd_vtarg_and_adv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mseg\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgamma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlam\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/baselines/pposgd/pposgd_simple.py\u001b[0m in \u001b[0;36mtraj_segment_generator\u001b[0;34m(pi, env, horizon, stochastic)\u001b[0m\n\u001b[1;32m 30\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0mprevac\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mac\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 32\u001b[0;31m \u001b[0mac\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvpred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpi\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mact\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstochastic\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mob\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 33\u001b[0m \u001b[0;31m# Slight weirdness here because we need value function at time T\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 34\u001b[0m \u001b[0;31m# before returning segment [0, T-1] so we get the correct\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m\u001b[0m in \u001b[0;36mact\u001b[0;34m(self, stochastic, ob)\u001b[0m\n\u001b[1;32m 43\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 44\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mact\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstochastic\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mob\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 45\u001b[0;31m \u001b[0mac1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvpred1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_act\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mstochastic\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mob\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 46\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mac1\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvpred1\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 47\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mget_variables\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/baselines/common/tf_util.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 443\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0minpt\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgivens\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 444\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0minpt\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minpt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgivens\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0minpt\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 445\u001b[0;31m \u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_session\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs_update\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfeed_dict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 446\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcheck_nan\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 447\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0misnan\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0many\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mr\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mresults\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 787\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 788\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[0;32m--> 789\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 790\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 791\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_run\u001b[0;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 995\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mfinal_fetches\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mfinal_targets\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 996\u001b[0m results = self._do_run(handle, final_targets, final_fetches,\n\u001b[0;32m--> 997\u001b[0;31m feed_dict_string, options, run_metadata)\n\u001b[0m\u001b[1;32m 998\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 999\u001b[0m \u001b[0mresults\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_do_run\u001b[0;34m(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 1130\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mhandle\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1131\u001b[0m return self._do_call(_run_fn, self._session, feed_dict, fetch_list,\n\u001b[0;32m-> 1132\u001b[0;31m target_list, options, run_metadata)\n\u001b[0m\u001b[1;32m 1133\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1134\u001b[0m return self._do_call(_prun_fn, self._session, handle, feed_dict,\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_do_call\u001b[0;34m(self, fn, *args)\u001b[0m\n\u001b[1;32m 1137\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_do_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1138\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1139\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1140\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mOpError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1141\u001b[0m \u001b[0mmessage\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcompat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mas_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;32m/home/isisilon/.pyenv/versions/3.6.0/envs/jupyter3/lib/python3.6/site-packages/tensorflow/python/client/session.py\u001b[0m in \u001b[0;36m_run_fn\u001b[0;34m(session, feed_dict, fetch_list, target_list, options, run_metadata)\u001b[0m\n\u001b[1;32m 1119\u001b[0m return tf_session.TF_Run(session, options,\n\u001b[1;32m 1120\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget_list\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1121\u001b[0;31m status, run_metadata)\n\u001b[0m\u001b[1;32m 1122\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1123\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_prun_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msession\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfeed_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfetch_list\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00475 |\n", + "| loss_pol_entpen | -0.0964 |\n", + "| loss_vf_loss | 8.54e-09 |\n", + "| loss_kl | 0.000777 |\n", + "| loss_ent | 9.64 |\n", + "| ev_tdlam_before | -0.00312 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 114 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.0964 |\n", + "| loss_vf_loss | 1.74e-09 |\n", + "| loss_kl | 0.000209 |\n", + "| loss_ent | 9.64 |\n", + "| ev_tdlam_before | -0.0482 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 115 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.0964 |\n", + "| loss_vf_loss | 4.14e-09 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 9.64 |\n", + "| ev_tdlam_before | 0.000929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 116 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00365 |\n", + "| loss_pol_entpen | -0.0967 |\n", + "| loss_vf_loss | 6.47e-10 |\n", + "| loss_kl | 0.000426 |\n", + "| loss_ent | 9.67 |\n", + "| ev_tdlam_before | -0.0503 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 118 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00691 |\n", + "| loss_pol_entpen | -0.0971 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000991 |\n", + "| loss_ent | 9.71 |\n", + "| ev_tdlam_before | -0.305 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 119 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00772 |\n", + "| loss_pol_entpen | -0.0976 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 0.00111 |\n", + "| loss_ent | 9.76 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 14 |\n", + "| TimestepsSoFar | 2.02e+04 |\n", + "| TimeElapsed | 120 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00519 |\n", + "| loss_pol_entpen | -0.0984 |\n", + "| loss_vf_loss | 4.1e-09 |\n", + "| loss_kl | 0.00067 |\n", + "| loss_ent | 9.84 |\n", + "| ev_tdlam_before | 0.000179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 129 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.0984 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 0.000317 |\n", + "| loss_ent | 9.84 |\n", + "| ev_tdlam_before | 0.00325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 130 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0103 |\n", + "| loss_pol_entpen | -0.0981 |\n", + "| loss_vf_loss | 1.22e-09 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 9.81 |\n", + "| ev_tdlam_before | -0.0258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 131 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00501 |\n", + "| loss_pol_entpen | -0.0981 |\n", + "| loss_vf_loss | 4.87e-10 |\n", + "| loss_kl | 0.000893 |\n", + "| loss_ent | 9.81 |\n", + "| ev_tdlam_before | 0.000291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 133 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00571 |\n", + "| loss_pol_entpen | -0.0983 |\n", + "| loss_vf_loss | 2.98e-10 |\n", + "| loss_kl | 0.000831 |\n", + "| loss_ent | 9.83 |\n", + "| ev_tdlam_before | -0.135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 134 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0035 |\n", + "| loss_pol_entpen | -0.0984 |\n", + "| loss_vf_loss | 5.73e-10 |\n", + "| loss_kl | 0.000508 |\n", + "| loss_ent | 9.84 |\n", + "| ev_tdlam_before | -0.00308 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 16 |\n", + "| TimestepsSoFar | 2.3e+04 |\n", + "| TimeElapsed | 135 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00351 |\n", + "| loss_pol_entpen | -0.101 |\n", + "| loss_vf_loss | 3.47e-09 |\n", + "| loss_kl | 0.000941 |\n", + "| loss_ent | 10.1 |\n", + "| ev_tdlam_before | -0.0219 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 18 |\n", + "| TimestepsSoFar | 2.59e+04 |\n", + "| TimeElapsed | 145 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00759 |\n", + "| loss_pol_entpen | -0.101 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | 0.000745 |\n", + "| loss_ent | 10.1 |\n", + "| ev_tdlam_before | -0.204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 18 |\n", + "| TimestepsSoFar | 2.59e+04 |\n", + "| TimeElapsed | 146 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0114 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 9.2e-10 |\n", + "| loss_kl | 0.00142 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.00156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 18 |\n", + "| TimestepsSoFar | 2.59e+04 |\n", + "| TimeElapsed | 147 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00575 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000716 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | 0.00442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 18 |\n", + "| TimestepsSoFar | 2.59e+04 |\n", + "| TimeElapsed | 149 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00406 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 5.55e-10 |\n", + "| loss_kl | 0.000414 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | 8.79e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 18 |\n", + "| TimestepsSoFar | 2.59e+04 |\n", + "| TimeElapsed | 150 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 4.28e-10 |\n", + "| loss_kl | 0.000487 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.0043 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 160 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0104 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 0.00125 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 161 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 4.47e-10 |\n", + "| loss_kl | 0.000408 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.00409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 162 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0118 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 3.14e-10 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.0292 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 164 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00751 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 6.09e-11 |\n", + "| loss_kl | 0.00105 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.000252 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 165 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0143 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 3.99e-09 |\n", + "| loss_kl | 0.00173 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.000684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 20 |\n", + "| TimestepsSoFar | 2.88e+04 |\n", + "| TimeElapsed | 166 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00484 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 6.65e-10 |\n", + "| loss_kl | 0.000402 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.00283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 175 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00633 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 2.07e-10 |\n", + "| loss_kl | 0.00073 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 176 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00825 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 3.44e-09 |\n", + "| loss_kl | 0.00112 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.00123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 177 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0045 |\n", + "| loss_pol_entpen | -0.102 |\n", + "| loss_vf_loss | 1.18e-09 |\n", + "| loss_kl | 0.000656 |\n", + "| loss_ent | 10.2 |\n", + "| ev_tdlam_before | -0.308 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 179 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00953 |\n", + "| loss_pol_entpen | -0.103 |\n", + "| loss_vf_loss | 3.22e-10 |\n", + "| loss_kl | 0.00113 |\n", + "| loss_ent | 10.3 |\n", + "| ev_tdlam_before | -0.17 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 180 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00474 |\n", + "| loss_pol_entpen | -0.103 |\n", + "| loss_vf_loss | 9.48e-11 |\n", + "| loss_kl | 0.000553 |\n", + "| loss_ent | 10.3 |\n", + "| ev_tdlam_before | -0.0106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 22 |\n", + "| TimestepsSoFar | 3.17e+04 |\n", + "| TimeElapsed | 182 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00653 |\n", + "| loss_pol_entpen | -0.104 |\n", + "| loss_vf_loss | 4.09e-09 |\n", + "| loss_kl | 0.00051 |\n", + "| loss_ent | 10.4 |\n", + "| ev_tdlam_before | -0.151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 190 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0133 |\n", + "| loss_pol_entpen | -0.105 |\n", + "| loss_vf_loss | 3.64e-09 |\n", + "| loss_kl | 0.00183 |\n", + "| loss_ent | 10.5 |\n", + "| ev_tdlam_before | -0.0152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 191 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0105 |\n", + "| loss_pol_entpen | -0.105 |\n", + "| loss_vf_loss | 8.89e-09 |\n", + "| loss_kl | 0.0016 |\n", + "| loss_ent | 10.5 |\n", + "| ev_tdlam_before | -0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 192 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00707 |\n", + "| loss_pol_entpen | -0.105 |\n", + "| loss_vf_loss | 8.38e-10 |\n", + "| loss_kl | 0.00108 |\n", + "| loss_ent | 10.5 |\n", + "| ev_tdlam_before | -0.239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 194 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.004 |\n", + "| loss_pol_entpen | -0.105 |\n", + "| loss_vf_loss | 1.93e-09 |\n", + "| loss_kl | 0.00072 |\n", + "| loss_ent | 10.5 |\n", + "| ev_tdlam_before | -0.175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 195 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0095 |\n", + "| loss_pol_entpen | -0.106 |\n", + "| loss_vf_loss | 4.55e-10 |\n", + "| loss_kl | 0.000812 |\n", + "| loss_ent | 10.6 |\n", + "| ev_tdlam_before | -0.00949 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 24 |\n", + "| TimestepsSoFar | 3.46e+04 |\n", + "| TimeElapsed | 197 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00505 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 4.63e-10 |\n", + "| loss_kl | 0.00076 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.00521 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 26 |\n", + "| TimestepsSoFar | 3.74e+04 |\n", + "| TimeElapsed | 206 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00373 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 2.91e-09 |\n", + "| loss_kl | 0.000409 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.00748 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 26 |\n", + "| TimestepsSoFar | 3.74e+04 |\n", + "| TimeElapsed | 207 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00197 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 6.75e-11 |\n", + "| loss_kl | 0.00022 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.477 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 26 |\n", + "| TimestepsSoFar | 3.74e+04 |\n", + "| TimeElapsed | 209 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00876 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 3.69e-09 |\n", + "| loss_kl | 0.000698 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.00403 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 26 |\n", + "| TimestepsSoFar | 3.74e+04 |\n", + "| TimeElapsed | 210 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00914 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 1.24e-09 |\n", + "| loss_kl | 0.00131 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 26 |\n", + "| TimestepsSoFar | 3.74e+04 |\n", + "| TimeElapsed | 211 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00485 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 8.61e-10 |\n", + "| loss_kl | 0.000788 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.00839 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 221 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 5.43e-10 |\n", + "| loss_kl | 0.000272 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 222 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 2.88e-10 |\n", + "| loss_kl | 0.000377 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.00262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 224 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00621 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 4.32e-10 |\n", + "| loss_kl | 0.000719 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0265 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 225 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00505 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 6.9e-11 |\n", + "| loss_kl | 0.000774 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.00631 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 226 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0076 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 3.75e-10 |\n", + "| loss_kl | 0.000933 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 28 |\n", + "| TimestepsSoFar | 4.03e+04 |\n", + "| TimeElapsed | 228 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00681 |\n", + "| loss_pol_entpen | -0.107 |\n", + "| loss_vf_loss | 3.99e-10 |\n", + "| loss_kl | 0.000601 |\n", + "| loss_ent | 10.7 |\n", + "| ev_tdlam_before | -0.0323 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 236 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00932 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 1.05e-08 |\n", + "| loss_kl | 0.000665 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | 0.0262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 237 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.00064 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.388 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 239 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00572 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 1.8e-09 |\n", + "| loss_kl | 0.000511 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | 0.000877 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 240 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0071 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 8.54e-10 |\n", + "| loss_kl | 0.000861 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 241 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00681 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 8.66e-10 |\n", + "| loss_kl | 0.000612 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.00684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 30 |\n", + "| TimestepsSoFar | 4.32e+04 |\n", + "| TimeElapsed | 243 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00753 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 4.15e-10 |\n", + "| loss_kl | 0.000554 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 251 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00872 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 2.57e-09 |\n", + "| loss_kl | 0.000831 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.0171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 252 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00685 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 0.000805 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0609 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 254 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00371 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 3.41e-10 |\n", + "| loss_kl | 0.000413 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | 0.000412 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 255 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0136 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 5.04e-10 |\n", + "| loss_kl | 0.0014 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | 0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 256 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00275 |\n", + "| loss_pol_entpen | -0.108 |\n", + "| loss_vf_loss | 1.56e-09 |\n", + "| loss_kl | 0.00076 |\n", + "| loss_ent | 10.8 |\n", + "| ev_tdlam_before | -0.0696 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 32 |\n", + "| TimestepsSoFar | 4.61e+04 |\n", + "| TimeElapsed | 258 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 1.09e-09 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | 0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 34 |\n", + "| TimestepsSoFar | 4.9e+04 |\n", + "| TimeElapsed | 267 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00796 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 1.15e-09 |\n", + "| loss_kl | 0.000727 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0273 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 34 |\n", + "| TimestepsSoFar | 4.9e+04 |\n", + "| TimeElapsed | 269 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00546 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 0.00083 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 34 |\n", + "| TimestepsSoFar | 4.9e+04 |\n", + "| TimeElapsed | 270 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00446 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 5.05e-11 |\n", + "| loss_kl | 0.000681 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0407 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 34 |\n", + "| TimestepsSoFar | 4.9e+04 |\n", + "| TimeElapsed | 271 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0123 |\n", + "| loss_pol_entpen | -0.109 |\n", + "| loss_vf_loss | 2.47e-09 |\n", + "| loss_kl | 0.0013 |\n", + "| loss_ent | 10.9 |\n", + "| ev_tdlam_before | -0.0065 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 34 |\n", + "| TimestepsSoFar | 4.9e+04 |\n", + "| TimeElapsed | 273 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0102 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 3.02e-10 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.00246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 282 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0041 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 8.01e-10 |\n", + "| loss_kl | 0.000585 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.0518 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 284 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00596 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000791 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.0994 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 285 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 1.07e-09 |\n", + "| loss_kl | 0.000598 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0009 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 286 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0046 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 0.000395 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.00146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 288 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0089 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 9.77e-10 |\n", + "| loss_kl | 0.000818 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.0178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000188 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 36 |\n", + "| TimestepsSoFar | 5.18e+04 |\n", + "| TimeElapsed | 289 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00469 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 8.34e-10 |\n", + "| loss_kl | 0.000747 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00507 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 297 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0132 |\n", + "| loss_pol_entpen | -0.114 |\n", + "| loss_vf_loss | 7.02e-10 |\n", + "| loss_kl | 0.00142 |\n", + "| loss_ent | 11.4 |\n", + "| ev_tdlam_before | 0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 299 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00596 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 6.94e-10 |\n", + "| loss_kl | 0.000844 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0638 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 300 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00441 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 6.17e-10 |\n", + "| loss_kl | 0.000643 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 301 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00626 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 9.2e-10 |\n", + "| loss_kl | 0.000738 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00638 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 303 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000172 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 38 |\n", + "| TimestepsSoFar | 5.47e+04 |\n", + "| TimeElapsed | 304 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00988 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 1.11e-09 |\n", + "| loss_kl | 0.001 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 312 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 7.13e-11 |\n", + "| loss_kl | 0.000425 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00975 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 313 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 3.01e-10 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 315 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 4.25e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00447 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 316 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00814 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 7.73e-11 |\n", + "| loss_kl | 0.000793 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 318 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 6.39e-11 |\n", + "| loss_kl | 0.000475 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 40 |\n", + "| TimestepsSoFar | 5.76e+04 |\n", + "| TimeElapsed | 319 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 2.61e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 42 |\n", + "| TimestepsSoFar | 6.05e+04 |\n", + "| TimeElapsed | 329 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00689 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 7.61e-11 |\n", + "| loss_kl | 0.000519 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.000326 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 42 |\n", + "| TimestepsSoFar | 6.05e+04 |\n", + "| TimeElapsed | 330 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00883 |\n", + "| loss_pol_entpen | -0.112 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 0.000955 |\n", + "| loss_ent | 11.2 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 42 |\n", + "| TimestepsSoFar | 6.05e+04 |\n", + "| TimeElapsed | 331 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00523 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 0.000638 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 42 |\n", + "| TimestepsSoFar | 6.05e+04 |\n", + "| TimeElapsed | 333 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 6.68e-11 |\n", + "| loss_kl | 0.000651 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | 0.00631 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000184 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 42 |\n", + "| TimestepsSoFar | 6.05e+04 |\n", + "| TimeElapsed | 334 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 2.66e-10 |\n", + "| loss_kl | 0.00064 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | 0.00125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 344 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00502 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 4.42e-11 |\n", + "| loss_kl | 0.000493 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00815 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 345 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0105 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 1.63e-09 |\n", + "| loss_kl | 0.00114 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 346 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0078 |\n", + "| loss_pol_entpen | -0.113 |\n", + "| loss_vf_loss | 2.62e-10 |\n", + "| loss_kl | 0.000986 |\n", + "| loss_ent | 11.3 |\n", + "| ev_tdlam_before | -0.051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 348 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00899 |\n", + "| loss_pol_entpen | -0.114 |\n", + "| loss_vf_loss | 6.39e-11 |\n", + "| loss_kl | 0.0013 |\n", + "| loss_ent | 11.4 |\n", + "| ev_tdlam_before | -0.000195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 349 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00988 |\n", + "| loss_pol_entpen | -0.114 |\n", + "| loss_vf_loss | 5.08e-10 |\n", + "| loss_kl | 0.00128 |\n", + "| loss_ent | 11.4 |\n", + "| ev_tdlam_before | -0.00741 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 44 |\n", + "| TimestepsSoFar | 6.34e+04 |\n", + "| TimeElapsed | 350 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00846 |\n", + "| loss_pol_entpen | -0.115 |\n", + "| loss_vf_loss | 5.93e-10 |\n", + "| loss_kl | 0.000947 |\n", + "| loss_ent | 11.5 |\n", + "| ev_tdlam_before | -0.058 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 359 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00849 |\n", + "| loss_pol_entpen | -0.116 |\n", + "| loss_vf_loss | 5.98e-11 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 11.6 |\n", + "| ev_tdlam_before | -0.0925 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 360 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00749 |\n", + "| loss_pol_entpen | -0.116 |\n", + "| loss_vf_loss | 4.51e-10 |\n", + "| loss_kl | 0.000789 |\n", + "| loss_ent | 11.6 |\n", + "| ev_tdlam_before | -0.0384 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 361 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00545 |\n", + "| loss_pol_entpen | -0.115 |\n", + "| loss_vf_loss | 7.77e-11 |\n", + "| loss_kl | 0.000681 |\n", + "| loss_ent | 11.5 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 363 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00491 |\n", + "| loss_pol_entpen | -0.116 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000746 |\n", + "| loss_ent | 11.6 |\n", + "| ev_tdlam_before | -0.0146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 364 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0109 |\n", + "| loss_pol_entpen | -0.116 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.00129 |\n", + "| loss_ent | 11.6 |\n", + "| ev_tdlam_before | -0.0461 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 46 |\n", + "| TimestepsSoFar | 6.62e+04 |\n", + "| TimeElapsed | 365 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00937 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.00113 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | -0.2 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 374 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0059 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 1.68e-09 |\n", + "| loss_kl | 0.000851 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | -0.037 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 375 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00421 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 1.61e-09 |\n", + "| loss_kl | 0.000412 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | -0.193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 376 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00912 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.000865 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | -0.0536 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 378 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0116 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 3.62e-10 |\n", + "| loss_kl | 0.00131 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | 0.000963 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 379 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00647 |\n", + "| loss_pol_entpen | -0.117 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 0.00108 |\n", + "| loss_ent | 11.7 |\n", + "| ev_tdlam_before | -0.0399 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 48 |\n", + "| TimestepsSoFar | 6.91e+04 |\n", + "| TimeElapsed | 380 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00695 |\n", + "| loss_pol_entpen | -0.118 |\n", + "| loss_vf_loss | 9.7e-11 |\n", + "| loss_kl | 0.00117 |\n", + "| loss_ent | 11.8 |\n", + "| ev_tdlam_before | -0.123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 50 |\n", + "| TimestepsSoFar | 7.2e+04 |\n", + "| TimeElapsed | 390 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.118 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 0.000498 |\n", + "| loss_ent | 11.8 |\n", + "| ev_tdlam_before | -0.00256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 50 |\n", + "| TimestepsSoFar | 7.2e+04 |\n", + "| TimeElapsed | 391 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00686 |\n", + "| loss_pol_entpen | -0.118 |\n", + "| loss_vf_loss | 4.73e-11 |\n", + "| loss_kl | 0.000757 |\n", + "| loss_ent | 11.8 |\n", + "| ev_tdlam_before | -0.018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 50 |\n", + "| TimestepsSoFar | 7.2e+04 |\n", + "| TimeElapsed | 393 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000384 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 50 |\n", + "| TimestepsSoFar | 7.2e+04 |\n", + "| TimeElapsed | 394 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00512 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 1.43e-09 |\n", + "| loss_kl | 0.000548 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | 0.0189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 50 |\n", + "| TimestepsSoFar | 7.2e+04 |\n", + "| TimeElapsed | 395 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00707 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 2.48e-09 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.0567 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 405 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.0919 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 406 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 3.15e-10 |\n", + "| loss_kl | 0.000234 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.00138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 408 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0077 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 2.76e-10 |\n", + "| loss_kl | 0.000833 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | 0.00159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 409 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 3.27e-10 |\n", + "| loss_kl | 0.000569 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 410 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00632 |\n", + "| loss_pol_entpen | -0.119 |\n", + "| loss_vf_loss | 3.99e-10 |\n", + "| loss_kl | 0.000582 |\n", + "| loss_ent | 11.9 |\n", + "| ev_tdlam_before | -0.0439 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 52 |\n", + "| TimestepsSoFar | 7.49e+04 |\n", + "| TimeElapsed | 412 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00516 |\n", + "| loss_pol_entpen | -0.12 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 0.000477 |\n", + "| loss_ent | 12 |\n", + "| ev_tdlam_before | -0.0372 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 420 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00459 |\n", + "| loss_pol_entpen | -0.12 |\n", + "| loss_vf_loss | 7.26e-10 |\n", + "| loss_kl | 0.000546 |\n", + "| loss_ent | 12 |\n", + "| ev_tdlam_before | 0.00339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 421 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0172 |\n", + "| loss_pol_entpen | -0.12 |\n", + "| loss_vf_loss | 1.84e-09 |\n", + "| loss_kl | 0.00124 |\n", + "| loss_ent | 12 |\n", + "| ev_tdlam_before | 0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 423 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00571 |\n", + "| loss_pol_entpen | -0.121 |\n", + "| loss_vf_loss | 7.87e-11 |\n", + "| loss_kl | 0.00107 |\n", + "| loss_ent | 12.1 |\n", + "| ev_tdlam_before | -0.19 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 424 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00348 |\n", + "| loss_pol_entpen | -0.121 |\n", + "| loss_vf_loss | 5.19e-10 |\n", + "| loss_kl | 0.000522 |\n", + "| loss_ent | 12.1 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 425 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00832 |\n", + "| loss_pol_entpen | -0.122 |\n", + "| loss_vf_loss | 2.92e-11 |\n", + "| loss_kl | 0.00104 |\n", + "| loss_ent | 12.2 |\n", + "| ev_tdlam_before | -0.0021 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 54 |\n", + "| TimestepsSoFar | 7.78e+04 |\n", + "| TimeElapsed | 427 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.123 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000387 |\n", + "| loss_ent | 12.3 |\n", + "| ev_tdlam_before | 0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 435 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0106 |\n", + "| loss_pol_entpen | -0.124 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 0.00109 |\n", + "| loss_ent | 12.4 |\n", + "| ev_tdlam_before | -0.00891 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 436 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00746 |\n", + "| loss_pol_entpen | -0.124 |\n", + "| loss_vf_loss | 1.73e-09 |\n", + "| loss_kl | 0.0014 |\n", + "| loss_ent | 12.4 |\n", + "| ev_tdlam_before | -0.108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 438 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0107 |\n", + "| loss_pol_entpen | -0.125 |\n", + "| loss_vf_loss | 1.07e-09 |\n", + "| loss_kl | 0.00147 |\n", + "| loss_ent | 12.5 |\n", + "| ev_tdlam_before | -0.203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 439 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0138 |\n", + "| loss_pol_entpen | -0.125 |\n", + "| loss_vf_loss | 1.04e-09 |\n", + "| loss_kl | 0.00173 |\n", + "| loss_ent | 12.5 |\n", + "| ev_tdlam_before | -0.08 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 440 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0103 |\n", + "| loss_pol_entpen | -0.126 |\n", + "| loss_vf_loss | 2.61e-10 |\n", + "| loss_kl | 0.00131 |\n", + "| loss_ent | 12.6 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 56 |\n", + "| TimestepsSoFar | 8.06e+04 |\n", + "| TimeElapsed | 442 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00846 |\n", + "| loss_pol_entpen | -0.128 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000931 |\n", + "| loss_ent | 12.8 |\n", + "| ev_tdlam_before | -0.00209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 58 |\n", + "| TimestepsSoFar | 8.35e+04 |\n", + "| TimeElapsed | 451 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0031 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 1.39e-09 |\n", + "| loss_kl | 0.000509 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.0559 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 58 |\n", + "| TimestepsSoFar | 8.35e+04 |\n", + "| TimeElapsed | 452 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 1.36e-09 |\n", + "| loss_kl | 0.000502 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.0657 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 58 |\n", + "| TimestepsSoFar | 8.35e+04 |\n", + "| TimeElapsed | 454 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0083 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 7.49e-11 |\n", + "| loss_kl | 0.000888 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.16 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 58 |\n", + "| TimestepsSoFar | 8.35e+04 |\n", + "| TimeElapsed | 455 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00441 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 3.25e-10 |\n", + "| loss_kl | 0.000684 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | 0.000702 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 58 |\n", + "| TimestepsSoFar | 8.35e+04 |\n", + "| TimeElapsed | 457 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00612 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 1.68e-09 |\n", + "| loss_kl | 0.000966 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.000133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 466 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0126 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.0014 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.0521 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 467 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00813 |\n", + "| loss_pol_entpen | -0.128 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.0012 |\n", + "| loss_ent | 12.8 |\n", + "| ev_tdlam_before | 9.06e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 469 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.128 |\n", + "| loss_vf_loss | 3.39e-10 |\n", + "| loss_kl | 0.00027 |\n", + "| loss_ent | 12.8 |\n", + "| ev_tdlam_before | -0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 470 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.004 |\n", + "| loss_pol_entpen | -0.128 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 0.000313 |\n", + "| loss_ent | 12.8 |\n", + "| ev_tdlam_before | 0.027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 472 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00295 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 4.81e-11 |\n", + "| loss_kl | 0.000451 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.0546 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 60 |\n", + "| TimestepsSoFar | 8.64e+04 |\n", + "| TimeElapsed | 473 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0043 |\n", + "| loss_pol_entpen | -0.129 |\n", + "| loss_vf_loss | 3.13e-09 |\n", + "| loss_kl | 0.000312 |\n", + "| loss_ent | 12.9 |\n", + "| ev_tdlam_before | -0.00214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 481 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00653 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 7.12e-10 |\n", + "| loss_kl | 0.000768 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.12 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 482 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 0.000491 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.0644 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 484 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00613 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000562 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.0177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 485 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 7.96e-10 |\n", + "| loss_kl | 0.000596 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 487 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00619 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000656 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.0629 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 62 |\n", + "| TimestepsSoFar | 8.93e+04 |\n", + "| TimeElapsed | 488 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 2.13e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | 0.00682 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 496 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00517 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 8.86e-10 |\n", + "| loss_kl | 0.000415 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.00728 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 497 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00522 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 7.5e-10 |\n", + "| loss_kl | 0.000702 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.0636 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 499 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00688 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 0.000906 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 500 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00714 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 8.75e-11 |\n", + "| loss_kl | 0.000842 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | 0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 502 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00704 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000888 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.00144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 64 |\n", + "| TimestepsSoFar | 9.22e+04 |\n", + "| TimeElapsed | 503 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 9.11e-10 |\n", + "| loss_kl | 0.000354 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.00657 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 66 |\n", + "| TimestepsSoFar | 9.5e+04 |\n", + "| TimeElapsed | 512 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 3.37e-10 |\n", + "| loss_kl | 0.000333 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.0298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 66 |\n", + "| TimestepsSoFar | 9.5e+04 |\n", + "| TimeElapsed | 514 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00624 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000717 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | 0.00332 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 66 |\n", + "| TimestepsSoFar | 9.5e+04 |\n", + "| TimeElapsed | 515 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00546 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.48e-09 |\n", + "| loss_kl | 0.000764 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.000801 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 66 |\n", + "| TimestepsSoFar | 9.5e+04 |\n", + "| TimeElapsed | 517 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00927 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 2.52e-10 |\n", + "| loss_kl | 0.00145 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 66 |\n", + "| TimestepsSoFar | 9.5e+04 |\n", + "| TimeElapsed | 518 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00572 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 0.000546 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.00051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 528 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00816 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 3.45e-10 |\n", + "| loss_kl | 0.000838 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.00985 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 529 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00393 |\n", + "| loss_pol_entpen | -0.13 |\n", + "| loss_vf_loss | 7.43e-10 |\n", + "| loss_kl | 0.000591 |\n", + "| loss_ent | 13 |\n", + "| ev_tdlam_before | -0.0544 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 530 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00879 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 6.61e-11 |\n", + "| loss_kl | 0.00116 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.0146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 532 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00722 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 0.00105 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | 0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 533 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.131 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 0.000195 |\n", + "| loss_ent | 13.1 |\n", + "| ev_tdlam_before | -0.00383 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 68 |\n", + "| TimestepsSoFar | 9.79e+04 |\n", + "| TimeElapsed | 535 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.133 |\n", + "| loss_vf_loss | 3.3e-10 |\n", + "| loss_kl | 0.000172 |\n", + "| loss_ent | 13.3 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 543 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.132 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 13.2 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 544 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0105 |\n", + "| loss_pol_entpen | -0.132 |\n", + "| loss_vf_loss | 4.71e-10 |\n", + "| loss_kl | 0.000865 |\n", + "| loss_ent | 13.2 |\n", + "| ev_tdlam_before | -0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 546 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.133 |\n", + "| loss_vf_loss | 6.76e-11 |\n", + "| loss_kl | 0.000442 |\n", + "| loss_ent | 13.3 |\n", + "| ev_tdlam_before | -0.0392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 547 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00484 |\n", + "| loss_pol_entpen | -0.133 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.000603 |\n", + "| loss_ent | 13.3 |\n", + "| ev_tdlam_before | -7.84e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 548 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.006 |\n", + "| loss_pol_entpen | -0.132 |\n", + "| loss_vf_loss | 3.76e-10 |\n", + "| loss_kl | 0.000639 |\n", + "| loss_ent | 13.2 |\n", + "| ev_tdlam_before | 0.000811 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 70 |\n", + "| TimestepsSoFar | 1.01e+05 |\n", + "| TimeElapsed | 550 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00608 |\n", + "| loss_pol_entpen | -0.134 |\n", + "| loss_vf_loss | 6.6e-10 |\n", + "| loss_kl | 0.000539 |\n", + "| loss_ent | 13.4 |\n", + "| ev_tdlam_before | 0.000351 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 558 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00584 |\n", + "| loss_pol_entpen | -0.133 |\n", + "| loss_vf_loss | 8.79e-11 |\n", + "| loss_kl | 0.000401 |\n", + "| loss_ent | 13.3 |\n", + "| ev_tdlam_before | -0.0594 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 559 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00392 |\n", + "| loss_pol_entpen | -0.134 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 0.000269 |\n", + "| loss_ent | 13.4 |\n", + "| ev_tdlam_before | -0.000366 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 560 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00681 |\n", + "| loss_pol_entpen | -0.134 |\n", + "| loss_vf_loss | 8.29e-10 |\n", + "| loss_kl | 0.000856 |\n", + "| loss_ent | 13.4 |\n", + "| ev_tdlam_before | 0.00148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 562 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.134 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 13.4 |\n", + "| ev_tdlam_before | -0.0684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 563 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00617 |\n", + "| loss_pol_entpen | -0.134 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 0.00072 |\n", + "| loss_ent | 13.4 |\n", + "| ev_tdlam_before | -0.00658 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 72 |\n", + "| TimestepsSoFar | 1.04e+05 |\n", + "| TimeElapsed | 565 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0046 |\n", + "| loss_pol_entpen | -0.135 |\n", + "| loss_vf_loss | 9.52e-10 |\n", + "| loss_kl | 0.000702 |\n", + "| loss_ent | 13.5 |\n", + "| ev_tdlam_before | -0.00127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 74 |\n", + "| TimestepsSoFar | 1.07e+05 |\n", + "| TimeElapsed | 574 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00681 |\n", + "| loss_pol_entpen | -0.135 |\n", + "| loss_vf_loss | 2.43e-10 |\n", + "| loss_kl | 0.000943 |\n", + "| loss_ent | 13.5 |\n", + "| ev_tdlam_before | -0.0142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 74 |\n", + "| TimestepsSoFar | 1.07e+05 |\n", + "| TimeElapsed | 575 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00559 |\n", + "| loss_pol_entpen | -0.135 |\n", + "| loss_vf_loss | 6.61e-10 |\n", + "| loss_kl | 0.000723 |\n", + "| loss_ent | 13.5 |\n", + "| ev_tdlam_before | 0.0073 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 74 |\n", + "| TimestepsSoFar | 1.07e+05 |\n", + "| TimeElapsed | 577 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00441 |\n", + "| loss_pol_entpen | -0.135 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000624 |\n", + "| loss_ent | 13.5 |\n", + "| ev_tdlam_before | -0.0922 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 74 |\n", + "| TimestepsSoFar | 1.07e+05 |\n", + "| TimeElapsed | 578 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0023 |\n", + "| loss_pol_entpen | -0.136 |\n", + "| loss_vf_loss | 4.9e-10 |\n", + "| loss_kl | 0.000283 |\n", + "| loss_ent | 13.6 |\n", + "| ev_tdlam_before | -0.0506 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 74 |\n", + "| TimestepsSoFar | 1.07e+05 |\n", + "| TimeElapsed | 579 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00324 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 7.54e-10 |\n", + "| loss_kl | 0.000491 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.062 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 589 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00228 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 3.38e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0494 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 590 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 5.06e-10 |\n", + "| loss_kl | 0.000402 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.00685 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 592 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00397 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 5.6e-08 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | 0.000301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 593 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00401 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 1.83e-10 |\n", + "| loss_kl | 0.000312 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | -1.04 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 594 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00758 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 4.49e-10 |\n", + "| loss_kl | 0.000762 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | -0.0355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 76 |\n", + "| TimestepsSoFar | 1.09e+05 |\n", + "| TimeElapsed | 596 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00605 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000716 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | 0.00444 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 604 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000475 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | 0.0284 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 605 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00645 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 6.16e-10 |\n", + "| loss_kl | 0.000523 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | -0.000978 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 606 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00622 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 2.25e-09 |\n", + "| loss_kl | 0.000601 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | 0.00131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 608 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00537 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 2.01e-09 |\n", + "| loss_kl | 0.000968 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 609 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0112 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 7.43e-10 |\n", + "| loss_kl | 0.00129 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000177 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 78 |\n", + "| TimestepsSoFar | 1.12e+05 |\n", + "| TimeElapsed | 610 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00437 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 6.83e-11 |\n", + "| loss_kl | 0.000597 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0512 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 619 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00574 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 4.25e-11 |\n", + "| loss_kl | 0.000335 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | -0.0181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 620 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0106 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 0.000864 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 621 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00706 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 5.56e-11 |\n", + "| loss_kl | 0.00117 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 623 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00554 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 6.2e-11 |\n", + "| loss_kl | 0.000842 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | 0.00785 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 624 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00419 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 8.04e-10 |\n", + "| loss_kl | 0.000336 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | 0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000179 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 80 |\n", + "| TimestepsSoFar | 1.15e+05 |\n", + "| TimeElapsed | 625 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00982 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.00143 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.00495 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000183 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 82 |\n", + "| TimestepsSoFar | 1.18e+05 |\n", + "| TimeElapsed | 635 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00298 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.48e-09 |\n", + "| loss_kl | 0.000542 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.000865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000183 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 82 |\n", + "| TimestepsSoFar | 1.18e+05 |\n", + "| TimeElapsed | 636 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00754 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 8.04e-11 |\n", + "| loss_kl | 0.000723 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000183 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 82 |\n", + "| TimestepsSoFar | 1.18e+05 |\n", + "| TimeElapsed | 638 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | 0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000183 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 82 |\n", + "| TimestepsSoFar | 1.18e+05 |\n", + "| TimeElapsed | 639 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000183 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 82 |\n", + "| TimestepsSoFar | 1.18e+05 |\n", + "| TimeElapsed | 640 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00497 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 3.61e-09 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | 0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 650 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00307 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 3.31e-09 |\n", + "| loss_kl | 0.000324 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | -0.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 651 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00351 |\n", + "| loss_pol_entpen | -0.137 |\n", + "| loss_vf_loss | 1.69e-09 |\n", + "| loss_kl | 0.000371 |\n", + "| loss_ent | 13.7 |\n", + "| ev_tdlam_before | -0.0197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 652 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00553 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000756 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 654 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00781 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 0.001 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 655 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0049 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 1.16e-09 |\n", + "| loss_kl | 0.000546 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | -0.00409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000182 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 84 |\n", + "| TimestepsSoFar | 1.21e+05 |\n", + "| TimeElapsed | 657 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00959 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 7.87e-10 |\n", + "| loss_kl | 0.00108 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | 0.00978 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 665 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00168 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 4.54e-11 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | -0.0282 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 666 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 4.46e-10 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | 0.000443 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 667 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00424 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | -0.0388 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 669 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00509 |\n", + "| loss_pol_entpen | -0.138 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.000472 |\n", + "| loss_ent | 13.8 |\n", + "| ev_tdlam_before | -0.0414 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 670 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0061 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 3.06e-10 |\n", + "| loss_kl | 0.000694 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | 0.00158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 86 |\n", + "| TimestepsSoFar | 1.24e+05 |\n", + "| TimeElapsed | 671 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0115 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 9.55e-10 |\n", + "| loss_kl | 0.00134 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | 0.00189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 680 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00754 |\n", + "| loss_pol_entpen | -0.139 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 0.00148 |\n", + "| loss_ent | 13.9 |\n", + "| ev_tdlam_before | -0.0472 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 681 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00427 |\n", + "| loss_pol_entpen | -0.14 |\n", + "| loss_vf_loss | 4.64e-10 |\n", + "| loss_kl | 0.000638 |\n", + "| loss_ent | 14 |\n", + "| ev_tdlam_before | -0.0929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 682 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.14 |\n", + "| loss_vf_loss | 7.9e-10 |\n", + "| loss_kl | 0.000717 |\n", + "| loss_ent | 14 |\n", + "| ev_tdlam_before | -0.00976 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 684 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00207 |\n", + "| loss_pol_entpen | -0.14 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000293 |\n", + "| loss_ent | 14 |\n", + "| ev_tdlam_before | -0.105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 685 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00758 |\n", + "| loss_pol_entpen | -0.141 |\n", + "| loss_vf_loss | 8.11e-10 |\n", + "| loss_kl | 0.000623 |\n", + "| loss_ent | 14.1 |\n", + "| ev_tdlam_before | -0.000402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 88 |\n", + "| TimestepsSoFar | 1.27e+05 |\n", + "| TimeElapsed | 686 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00448 |\n", + "| loss_pol_entpen | -0.142 |\n", + "| loss_vf_loss | 5.67e-10 |\n", + "| loss_kl | 0.000381 |\n", + "| loss_ent | 14.2 |\n", + "| ev_tdlam_before | 0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 90 |\n", + "| TimestepsSoFar | 1.3e+05 |\n", + "| TimeElapsed | 696 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00494 |\n", + "| loss_pol_entpen | -0.142 |\n", + "| loss_vf_loss | 4.25e-10 |\n", + "| loss_kl | 0.000781 |\n", + "| loss_ent | 14.2 |\n", + "| ev_tdlam_before | -0.0467 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 90 |\n", + "| TimestepsSoFar | 1.3e+05 |\n", + "| TimeElapsed | 697 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00946 |\n", + "| loss_pol_entpen | -0.143 |\n", + "| loss_vf_loss | 5.29e-10 |\n", + "| loss_kl | 0.00123 |\n", + "| loss_ent | 14.3 |\n", + "| ev_tdlam_before | -0.023 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 90 |\n", + "| TimestepsSoFar | 1.3e+05 |\n", + "| TimeElapsed | 699 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00345 |\n", + "| loss_pol_entpen | -0.143 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 0.000646 |\n", + "| loss_ent | 14.3 |\n", + "| ev_tdlam_before | -0.0488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 90 |\n", + "| TimestepsSoFar | 1.3e+05 |\n", + "| TimeElapsed | 700 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0102 |\n", + "| loss_pol_entpen | -0.144 |\n", + "| loss_vf_loss | 6.1e-10 |\n", + "| loss_kl | 0.00124 |\n", + "| loss_ent | 14.4 |\n", + "| ev_tdlam_before | -0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000189 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 90 |\n", + "| TimestepsSoFar | 1.3e+05 |\n", + "| TimeElapsed | 701 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.146 |\n", + "| loss_vf_loss | 2.57e-09 |\n", + "| loss_kl | 0.000414 |\n", + "| loss_ent | 14.6 |\n", + "| ev_tdlam_before | -0.0292 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 711 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00545 |\n", + "| loss_pol_entpen | -0.146 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 0.000313 |\n", + "| loss_ent | 14.6 |\n", + "| ev_tdlam_before | -0.0751 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 712 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00971 |\n", + "| loss_pol_entpen | -0.145 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0.00114 |\n", + "| loss_ent | 14.5 |\n", + "| ev_tdlam_before | -0.00828 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 713 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.146 |\n", + "| loss_vf_loss | 1.04e-09 |\n", + "| loss_kl | 0.000543 |\n", + "| loss_ent | 14.6 |\n", + "| ev_tdlam_before | -0.00266 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 715 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0129 |\n", + "| loss_pol_entpen | -0.146 |\n", + "| loss_vf_loss | 3.06e-09 |\n", + "| loss_kl | 0.00183 |\n", + "| loss_ent | 14.6 |\n", + "| ev_tdlam_before | -0.0405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 716 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0078 |\n", + "| loss_pol_entpen | -0.146 |\n", + "| loss_vf_loss | 4.8e-10 |\n", + "| loss_kl | 0.0011 |\n", + "| loss_ent | 14.6 |\n", + "| ev_tdlam_before | 0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 92 |\n", + "| TimestepsSoFar | 1.32e+05 |\n", + "| TimeElapsed | 717 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00216 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 4.32e-10 |\n", + "| loss_kl | 0.000322 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.0379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 726 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00501 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 0.000497 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.0568 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 727 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00605 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 7.83e-11 |\n", + "| loss_kl | 0.000786 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.00525 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 728 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00333 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000365 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | 0.0168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 730 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 4.24e-10 |\n", + "| loss_kl | 0.000385 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.000422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 731 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0031 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 1.9e-09 |\n", + "| loss_kl | 0.000259 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.000283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 94 |\n", + "| TimestepsSoFar | 1.35e+05 |\n", + "| TimeElapsed | 732 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.147 |\n", + "| loss_vf_loss | 1.17e-09 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 14.7 |\n", + "| ev_tdlam_before | -0.0374 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 740 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00379 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 9.56e-10 |\n", + "| loss_kl | 0.000459 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 742 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00168 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | 0.00457 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 743 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00317 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 5.79e-09 |\n", + "| loss_kl | 0.000292 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00528 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 745 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 0.000307 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 746 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00638 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.94e-10 |\n", + "| loss_kl | 0.000771 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | 0.004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 96 |\n", + "| TimestepsSoFar | 1.38e+05 |\n", + "| TimeElapsed | 748 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00397 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 3.96e-11 |\n", + "| loss_kl | 0.00068 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | 0.00177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 98 |\n", + "| TimestepsSoFar | 1.41e+05 |\n", + "| TimeElapsed | 757 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00971 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 0.000771 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | 0.0002 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 98 |\n", + "| TimestepsSoFar | 1.41e+05 |\n", + "| TimeElapsed | 759 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00998 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 6.18e-11 |\n", + "| loss_kl | 0.00132 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 98 |\n", + "| TimestepsSoFar | 1.41e+05 |\n", + "| TimeElapsed | 760 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 0.000155 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 98 |\n", + "| TimestepsSoFar | 1.41e+05 |\n", + "| TimeElapsed | 761 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00733 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000906 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00991 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 98 |\n", + "| TimestepsSoFar | 1.41e+05 |\n", + "| TimeElapsed | 763 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 1.9e-09 |\n", + "| loss_kl | 0.000513 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | 3.59e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 772 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00666 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.74e-09 |\n", + "| loss_kl | 0.000759 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | 0.00169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 774 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00445 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.89e-09 |\n", + "| loss_kl | 0.000408 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.0256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 775 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00982 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 7e-10 |\n", + "| loss_kl | 0.00113 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.000561 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 776 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00562 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 0.000915 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.00928 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 778 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00657 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.89e-09 |\n", + "| loss_kl | 0.000851 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | 0.00639 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 100 |\n", + "| TimestepsSoFar | 1.44e+05 |\n", + "| TimeElapsed | 779 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 8.74e-11 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 787 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 8.35e-11 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 0.00216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 788 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00325 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 2.61e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 0.00634 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 790 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 6.08e-11 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 0.00483 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 791 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00667 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | 0.000604 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | 0.00839 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 792 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00833 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 2.95e-09 |\n", + "| loss_kl | 0.000991 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 102 |\n", + "| TimestepsSoFar | 1.47e+05 |\n", + "| TimeElapsed | 794 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00458 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 6.14e-10 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 802 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00286 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 7.74e-11 |\n", + "| loss_kl | 0.000228 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.0264 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 803 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00797 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000866 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 805 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.00324 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 806 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00586 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 3.95e-10 |\n", + "| loss_kl | 0.000646 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.00282 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 807 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00492 |\n", + "| loss_pol_entpen | -0.148 |\n", + "| loss_vf_loss | 4.9e-10 |\n", + "| loss_kl | 0.000569 |\n", + "| loss_ent | 14.8 |\n", + "| ev_tdlam_before | -0.00638 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 104 |\n", + "| TimestepsSoFar | 1.5e+05 |\n", + "| TimeElapsed | 809 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 6.88e-10 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 106 |\n", + "| TimestepsSoFar | 1.53e+05 |\n", + "| TimeElapsed | 818 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 2.84e-10 |\n", + "| loss_kl | 0.00012 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | 0.00152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 106 |\n", + "| TimestepsSoFar | 1.53e+05 |\n", + "| TimeElapsed | 820 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00445 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 9.35e-10 |\n", + "| loss_kl | 0.000388 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -2.31e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 106 |\n", + "| TimestepsSoFar | 1.53e+05 |\n", + "| TimeElapsed | 821 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00805 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.000453 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | -0.044 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 106 |\n", + "| TimestepsSoFar | 1.53e+05 |\n", + "| TimeElapsed | 823 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00393 |\n", + "| loss_pol_entpen | -0.149 |\n", + "| loss_vf_loss | 3.35e-09 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 14.9 |\n", + "| ev_tdlam_before | 0.0035 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000195 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 106 |\n", + "| TimestepsSoFar | 1.53e+05 |\n", + "| TimeElapsed | 824 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000344 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.0258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 833 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00469 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000555 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.000722 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 835 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00576 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 8.89e-11 |\n", + "| loss_kl | 0.000666 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 836 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00711 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 1e-09 |\n", + "| loss_kl | 0.00115 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.000584 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 837 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000495 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 5.97e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.0601 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 839 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00389 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 8.79e-10 |\n", + "| loss_kl | 0.000232 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.0418 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 108 |\n", + "| TimestepsSoFar | 1.56e+05 |\n", + "| TimeElapsed | 840 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0118 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 3.69e-10 |\n", + "| loss_kl | 0.00141 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 4.6e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 848 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00461 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 2.41e-10 |\n", + "| loss_kl | 0.000969 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | 0.00473 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 849 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0113 |\n", + "| loss_pol_entpen | -0.15 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.00133 |\n", + "| loss_ent | 15 |\n", + "| ev_tdlam_before | -0.0312 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 851 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0131 |\n", + "| loss_pol_entpen | -0.151 |\n", + "| loss_vf_loss | 1.61e-09 |\n", + "| loss_kl | 0.00191 |\n", + "| loss_ent | 15.1 |\n", + "| ev_tdlam_before | -0.0224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 852 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.152 |\n", + "| loss_vf_loss | 2.78e-09 |\n", + "| loss_kl | 0.000542 |\n", + "| loss_ent | 15.2 |\n", + "| ev_tdlam_before | 0.00482 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 854 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00535 |\n", + "| loss_pol_entpen | -0.152 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 0.000568 |\n", + "| loss_ent | 15.2 |\n", + "| ev_tdlam_before | -0.181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000187 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 110 |\n", + "| TimestepsSoFar | 1.58e+05 |\n", + "| TimeElapsed | 855 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00617 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 6.34e-10 |\n", + "| loss_kl | 0.00085 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.00534 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 863 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0058 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 8.97e-10 |\n", + "| loss_kl | 0.000853 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.00277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 864 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00329 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000371 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.0496 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 866 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00634 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 4.12e-10 |\n", + "| loss_kl | 0.000872 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.00424 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 867 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00663 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 6.44e-10 |\n", + "| loss_kl | 0.000784 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.000153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 868 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000754 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 5.07e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.0644 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 112 |\n", + "| TimestepsSoFar | 1.61e+05 |\n", + "| TimeElapsed | 870 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00645 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 7.34e-10 |\n", + "| loss_kl | 0.000452 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | 0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 114 |\n", + "| TimestepsSoFar | 1.64e+05 |\n", + "| TimeElapsed | 879 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00381 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 6.73e-11 |\n", + "| loss_kl | 0.000652 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | -0.102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 114 |\n", + "| TimestepsSoFar | 1.64e+05 |\n", + "| TimeElapsed | 881 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 2.49e-10 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | 0.00275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 114 |\n", + "| TimestepsSoFar | 1.64e+05 |\n", + "| TimeElapsed | 882 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00462 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 0.000399 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | -0.00357 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 114 |\n", + "| TimestepsSoFar | 1.64e+05 |\n", + "| TimeElapsed | 883 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00744 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.000759 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.0203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 114 |\n", + "| TimestepsSoFar | 1.64e+05 |\n", + "| TimeElapsed | 885 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00317 |\n", + "| loss_pol_entpen | -0.153 |\n", + "| loss_vf_loss | 1.4e-09 |\n", + "| loss_kl | 0.000484 |\n", + "| loss_ent | 15.3 |\n", + "| ev_tdlam_before | -0.0178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 894 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00476 |\n", + "| loss_pol_entpen | -0.153 |\n", + "| loss_vf_loss | 1.35e-09 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 15.3 |\n", + "| ev_tdlam_before | -0.258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 896 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00372 |\n", + "| loss_pol_entpen | -0.153 |\n", + "| loss_vf_loss | 9.58e-11 |\n", + "| loss_kl | 0.000415 |\n", + "| loss_ent | 15.3 |\n", + "| ev_tdlam_before | 0.0161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 897 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0023 |\n", + "| loss_pol_entpen | -0.153 |\n", + "| loss_vf_loss | 9.44e-10 |\n", + "| loss_kl | 0.000291 |\n", + "| loss_ent | 15.3 |\n", + "| ev_tdlam_before | -0.0307 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 898 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00605 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 5.46e-10 |\n", + "| loss_kl | 0.000557 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 900 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.006 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 3.88e-10 |\n", + "| loss_kl | 0.000664 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.0223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 116 |\n", + "| TimestepsSoFar | 1.67e+05 |\n", + "| TimeElapsed | 901 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00312 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 2.06e-10 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | -0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 909 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00477 |\n", + "| loss_pol_entpen | -0.154 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000591 |\n", + "| loss_ent | 15.4 |\n", + "| ev_tdlam_before | 0.0201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 910 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00852 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 2.53e-11 |\n", + "| loss_kl | 0.00101 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | -0.0204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 912 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000449 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | -0.000216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 913 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.155 |\n", + "| loss_vf_loss | 7.46e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 15.5 |\n", + "| ev_tdlam_before | -0.000749 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 915 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00898 |\n", + "| loss_pol_entpen | -0.156 |\n", + "| loss_vf_loss | 4.84e-10 |\n", + "| loss_kl | 0.00121 |\n", + "| loss_ent | 15.6 |\n", + "| ev_tdlam_before | -0.221 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 118 |\n", + "| TimestepsSoFar | 1.7e+05 |\n", + "| TimeElapsed | 916 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000466 |\n", + "| loss_pol_entpen | -0.157 |\n", + "| loss_vf_loss | 1.08e-09 |\n", + "| loss_kl | 5.04e-05 |\n", + "| loss_ent | 15.7 |\n", + "| ev_tdlam_before | -0.0195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 924 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.157 |\n", + "| loss_vf_loss | 1.74e-09 |\n", + "| loss_kl | 0.000146 |\n", + "| loss_ent | 15.7 |\n", + "| ev_tdlam_before | -0.263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 925 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00422 |\n", + "| loss_pol_entpen | -0.157 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 15.7 |\n", + "| ev_tdlam_before | -0.0838 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 927 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0031 |\n", + "| loss_pol_entpen | -0.157 |\n", + "| loss_vf_loss | 3.48e-10 |\n", + "| loss_kl | 0.000492 |\n", + "| loss_ent | 15.7 |\n", + "| ev_tdlam_before | -0.0181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 928 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00506 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 3.22e-09 |\n", + "| loss_kl | 0.000732 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.0343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 929 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00726 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 1.56e-09 |\n", + "| loss_kl | 0.00076 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.0569 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 120 |\n", + "| TimestepsSoFar | 1.73e+05 |\n", + "| TimeElapsed | 931 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00279 |\n", + "| loss_pol_entpen | -0.157 |\n", + "| loss_vf_loss | 5.79e-10 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 15.7 |\n", + "| ev_tdlam_before | -6.22e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 122 |\n", + "| TimestepsSoFar | 1.76e+05 |\n", + "| TimeElapsed | 940 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00673 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 3.68e-10 |\n", + "| loss_kl | 0.000851 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | 0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 122 |\n", + "| TimestepsSoFar | 1.76e+05 |\n", + "| TimeElapsed | 942 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00705 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 0.000505 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | 0.00109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 122 |\n", + "| TimestepsSoFar | 1.76e+05 |\n", + "| TimeElapsed | 943 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00594 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 3.28e-10 |\n", + "| loss_kl | 0.000868 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | 0.00428 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 122 |\n", + "| TimestepsSoFar | 1.76e+05 |\n", + "| TimeElapsed | 944 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00591 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000645 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.00986 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 122 |\n", + "| TimestepsSoFar | 1.76e+05 |\n", + "| TimeElapsed | 946 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 3.23e-09 |\n", + "| loss_kl | 0.0005 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.00629 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 955 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0057 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 0.000743 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.00819 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 957 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0043 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 0.000608 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.00181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 958 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 3.71e-10 |\n", + "| loss_kl | 0.000338 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -8.01e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 959 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00577 |\n", + "| loss_pol_entpen | -0.158 |\n", + "| loss_vf_loss | 2.15e-09 |\n", + "| loss_kl | 0.000631 |\n", + "| loss_ent | 15.8 |\n", + "| ev_tdlam_before | -0.0766 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 961 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0173 |\n", + "| loss_pol_entpen | -0.159 |\n", + "| loss_vf_loss | 6.82e-10 |\n", + "| loss_kl | 0.00209 |\n", + "| loss_ent | 15.9 |\n", + "| ev_tdlam_before | -0.268 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 124 |\n", + "| TimestepsSoFar | 1.79e+05 |\n", + "| TimeElapsed | 962 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0145 |\n", + "| loss_pol_entpen | -0.16 |\n", + "| loss_vf_loss | 4.85e-10 |\n", + "| loss_kl | 0.00138 |\n", + "| loss_ent | 16 |\n", + "| ev_tdlam_before | -0.00502 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 970 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.16 |\n", + "| loss_vf_loss | 7.57e-10 |\n", + "| loss_kl | 0.001 |\n", + "| loss_ent | 16 |\n", + "| ev_tdlam_before | 0.00946 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 971 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00465 |\n", + "| loss_pol_entpen | -0.161 |\n", + "| loss_vf_loss | 6.16e-10 |\n", + "| loss_kl | 0.000607 |\n", + "| loss_ent | 16.1 |\n", + "| ev_tdlam_before | -0.0517 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 973 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00317 |\n", + "| loss_pol_entpen | -0.161 |\n", + "| loss_vf_loss | 5.88e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 16.1 |\n", + "| ev_tdlam_before | -0.0372 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 974 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.161 |\n", + "| loss_vf_loss | 8.27e-11 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 16.1 |\n", + "| ev_tdlam_before | -0.0871 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 975 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.161 |\n", + "| loss_vf_loss | 4.39e-10 |\n", + "| loss_kl | 0.000218 |\n", + "| loss_ent | 16.1 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 126 |\n", + "| TimestepsSoFar | 1.81e+05 |\n", + "| TimeElapsed | 977 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00529 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 3.14e-09 |\n", + "| loss_kl | 0.000523 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 985 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00989 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 9.24e-11 |\n", + "| loss_kl | 0.00107 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 986 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000664 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 0.000343 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | -0.0364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 988 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00411 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 7.3e-11 |\n", + "| loss_kl | 0.00043 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 989 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 7.45e-11 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | -0.0165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 990 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.162 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.00041 |\n", + "| loss_ent | 16.2 |\n", + "| ev_tdlam_before | 0.00384 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 128 |\n", + "| TimestepsSoFar | 1.84e+05 |\n", + "| TimeElapsed | 992 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0113 |\n", + "| loss_pol_entpen | -0.165 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.00174 |\n", + "| loss_ent | 16.5 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 130 |\n", + "| TimestepsSoFar | 1.87e+05 |\n", + "| TimeElapsed | 1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.165 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 0.000399 |\n", + "| loss_ent | 16.5 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 130 |\n", + "| TimestepsSoFar | 1.87e+05 |\n", + "| TimeElapsed | 1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00658 |\n", + "| loss_pol_entpen | -0.165 |\n", + "| loss_vf_loss | 5.49e-10 |\n", + "| loss_kl | 0.000669 |\n", + "| loss_ent | 16.5 |\n", + "| ev_tdlam_before | -0.00018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 130 |\n", + "| TimestepsSoFar | 1.87e+05 |\n", + "| TimeElapsed | 1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00366 |\n", + "| loss_pol_entpen | -0.165 |\n", + "| loss_vf_loss | 8.58e-11 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 16.5 |\n", + "| ev_tdlam_before | -0.00361 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 130 |\n", + "| TimestepsSoFar | 1.87e+05 |\n", + "| TimeElapsed | 1.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0142 |\n", + "| loss_pol_entpen | -0.165 |\n", + "| loss_vf_loss | 9.15e-10 |\n", + "| loss_kl | 0.00145 |\n", + "| loss_ent | 16.5 |\n", + "| ev_tdlam_before | 0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 130 |\n", + "| TimestepsSoFar | 1.87e+05 |\n", + "| TimeElapsed | 1.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0121 |\n", + "| loss_pol_entpen | -0.168 |\n", + "| loss_vf_loss | 9.89e-10 |\n", + "| loss_kl | 0.00119 |\n", + "| loss_ent | 16.8 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00518 |\n", + "| loss_pol_entpen | -0.169 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.00115 |\n", + "| loss_ent | 16.9 |\n", + "| ev_tdlam_before | -0.00102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00694 |\n", + "| loss_pol_entpen | -0.169 |\n", + "| loss_vf_loss | 2.83e-10 |\n", + "| loss_kl | 0.000779 |\n", + "| loss_ent | 16.9 |\n", + "| ev_tdlam_before | 0.00473 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000748 |\n", + "| loss_pol_entpen | -0.169 |\n", + "| loss_vf_loss | 7.46e-10 |\n", + "| loss_kl | 0.00033 |\n", + "| loss_ent | 16.9 |\n", + "| ev_tdlam_before | -0.0679 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00876 |\n", + "| loss_pol_entpen | -0.17 |\n", + "| loss_vf_loss | 4.41e-10 |\n", + "| loss_kl | 0.000995 |\n", + "| loss_ent | 17 |\n", + "| ev_tdlam_before | -0.00559 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00993 |\n", + "| loss_pol_entpen | -0.17 |\n", + "| loss_vf_loss | 1.09e-09 |\n", + "| loss_kl | 0.00141 |\n", + "| loss_ent | 17 |\n", + "| ev_tdlam_before | -0.0106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 132 |\n", + "| TimestepsSoFar | 1.9e+05 |\n", + "| TimeElapsed | 1.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | -0.00865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00287 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 4.47e-09 |\n", + "| loss_kl | 0.000375 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | -0.0293 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00467 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 2.14e-09 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | -0.676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00668 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 8.26e-10 |\n", + "| loss_kl | 0.000737 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | -0.0606 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00505 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 2.91e-10 |\n", + "| loss_kl | 0.000723 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | -0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00278 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 6.06e-11 |\n", + "| loss_kl | 0.000494 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | 0.00476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 134 |\n", + "| TimestepsSoFar | 1.93e+05 |\n", + "| TimeElapsed | 1.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.171 |\n", + "| loss_vf_loss | 5.6e-10 |\n", + "| loss_kl | 0.000663 |\n", + "| loss_ent | 17.1 |\n", + "| ev_tdlam_before | 5.9e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00518 |\n", + "| loss_pol_entpen | -0.172 |\n", + "| loss_vf_loss | 3.97e-10 |\n", + "| loss_kl | 0.000846 |\n", + "| loss_ent | 17.2 |\n", + "| ev_tdlam_before | -0.0489 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0123 |\n", + "| loss_pol_entpen | -0.172 |\n", + "| loss_vf_loss | 9.38e-10 |\n", + "| loss_kl | 0.00158 |\n", + "| loss_ent | 17.2 |\n", + "| ev_tdlam_before | -0.000163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00646 |\n", + "| loss_pol_entpen | -0.172 |\n", + "| loss_vf_loss | 2.01e-09 |\n", + "| loss_kl | 0.00101 |\n", + "| loss_ent | 17.2 |\n", + "| ev_tdlam_before | -0.0426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.172 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 0.000494 |\n", + "| loss_ent | 17.2 |\n", + "| ev_tdlam_before | -0.0321 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00449 |\n", + "| loss_pol_entpen | -0.172 |\n", + "| loss_vf_loss | 3.44e-10 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 17.2 |\n", + "| ev_tdlam_before | 0.00644 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 136 |\n", + "| TimestepsSoFar | 1.96e+05 |\n", + "| TimeElapsed | 1.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00374 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 7.08e-10 |\n", + "| loss_kl | 0.00037 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 138 |\n", + "| TimestepsSoFar | 1.99e+05 |\n", + "| TimeElapsed | 1.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00388 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 5.53e-10 |\n", + "| loss_kl | 0.000511 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.0216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 138 |\n", + "| TimestepsSoFar | 1.99e+05 |\n", + "| TimeElapsed | 1.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00406 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000541 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.0213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 138 |\n", + "| TimestepsSoFar | 1.99e+05 |\n", + "| TimeElapsed | 1.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00286 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 5.97e-10 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.0654 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 138 |\n", + "| TimestepsSoFar | 1.99e+05 |\n", + "| TimeElapsed | 1.07e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 2.92e-10 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 138 |\n", + "| TimestepsSoFar | 1.99e+05 |\n", + "| TimeElapsed | 1.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00601 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 5.09e-10 |\n", + "| loss_kl | 0.000474 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0056 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00515 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 6.21e-10 |\n", + "| loss_kl | 0.000661 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | 0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00436 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 9.05e-11 |\n", + "| loss_kl | 0.000318 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00312 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 5.5e-10 |\n", + "| loss_kl | 0.000426 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.002 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00723 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 5.05e-10 |\n", + "| loss_kl | 0.000603 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0907 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00549 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 8.85e-10 |\n", + "| loss_kl | 0.000737 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | 0.00897 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 140 |\n", + "| TimestepsSoFar | 2.02e+05 |\n", + "| TimeElapsed | 1.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00656 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 6.4e-10 |\n", + "| loss_kl | 0.000844 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 3.36e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0834 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00226 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 1.49e-09 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.0816 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 3.39e-11 |\n", + "| loss_kl | 0.000202 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00768 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.000837 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | 0.00573 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0059 |\n", + "| loss_pol_entpen | -0.173 |\n", + "| loss_vf_loss | 8.7e-11 |\n", + "| loss_kl | 0.000774 |\n", + "| loss_ent | 17.3 |\n", + "| ev_tdlam_before | -0.0267 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 142 |\n", + "| TimestepsSoFar | 2.04e+05 |\n", + "| TimeElapsed | 1.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00712 |\n", + "| loss_pol_entpen | -0.174 |\n", + "| loss_vf_loss | 4.38e-10 |\n", + "| loss_kl | 0.00107 |\n", + "| loss_ent | 17.4 |\n", + "| ev_tdlam_before | -0.00626 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00799 |\n", + "| loss_pol_entpen | -0.175 |\n", + "| loss_vf_loss | 1.42e-09 |\n", + "| loss_kl | 0.00123 |\n", + "| loss_ent | 17.5 |\n", + "| ev_tdlam_before | -0.0568 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.175 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 17.5 |\n", + "| ev_tdlam_before | -0.0731 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.175 |\n", + "| loss_vf_loss | 4.2e-10 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 17.5 |\n", + "| ev_tdlam_before | -0.000757 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.175 |\n", + "| loss_vf_loss | 8.6e-10 |\n", + "| loss_kl | 0.000464 |\n", + "| loss_ent | 17.5 |\n", + "| ev_tdlam_before | -0.000648 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.175 |\n", + "| loss_vf_loss | 8.51e-10 |\n", + "| loss_kl | 0.000313 |\n", + "| loss_ent | 17.5 |\n", + "| ev_tdlam_before | -0.039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 144 |\n", + "| TimestepsSoFar | 2.07e+05 |\n", + "| TimeElapsed | 1.11e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00478 |\n", + "| loss_pol_entpen | -0.177 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 0.000432 |\n", + "| loss_ent | 17.7 |\n", + "| ev_tdlam_before | 0.00271 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 146 |\n", + "| TimestepsSoFar | 2.1e+05 |\n", + "| TimeElapsed | 1.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.177 |\n", + "| loss_vf_loss | 9.72e-11 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 17.7 |\n", + "| ev_tdlam_before | -0.000281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 146 |\n", + "| TimestepsSoFar | 2.1e+05 |\n", + "| TimeElapsed | 1.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00546 |\n", + "| loss_pol_entpen | -0.177 |\n", + "| loss_vf_loss | 5.07e-10 |\n", + "| loss_kl | 0.000481 |\n", + "| loss_ent | 17.7 |\n", + "| ev_tdlam_before | -5.5e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 146 |\n", + "| TimestepsSoFar | 2.1e+05 |\n", + "| TimeElapsed | 1.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00342 |\n", + "| loss_pol_entpen | -0.177 |\n", + "| loss_vf_loss | 3.58e-09 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 17.7 |\n", + "| ev_tdlam_before | -0.0367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 146 |\n", + "| TimestepsSoFar | 2.1e+05 |\n", + "| TimeElapsed | 1.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00899 |\n", + "| loss_pol_entpen | -0.177 |\n", + "| loss_vf_loss | 3.13e-09 |\n", + "| loss_kl | 0.000969 |\n", + "| loss_ent | 17.7 |\n", + "| ev_tdlam_before | -0.17 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 146 |\n", + "| TimestepsSoFar | 2.1e+05 |\n", + "| TimeElapsed | 1.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00592 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 9.96e-10 |\n", + "| loss_kl | 0.000874 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | 0.00132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00781 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 8.13e-11 |\n", + "| loss_kl | 0.000775 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | -0.00493 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00516 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 2.74e-10 |\n", + "| loss_kl | 0.00046 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | -0.0227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 5.45e-11 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | -0.0147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00298 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 0.000467 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | 0.0033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.178 |\n", + "| loss_vf_loss | 4.74e-10 |\n", + "| loss_kl | 0.000377 |\n", + "| loss_ent | 17.8 |\n", + "| ev_tdlam_before | 0.0278 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 148 |\n", + "| TimestepsSoFar | 2.13e+05 |\n", + "| TimeElapsed | 1.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.179 |\n", + "| loss_vf_loss | 5.87e-11 |\n", + "| loss_kl | 0.000426 |\n", + "| loss_ent | 17.9 |\n", + "| ev_tdlam_before | 0.00171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.179 |\n", + "| loss_vf_loss | 2.48e-09 |\n", + "| loss_kl | 0.000378 |\n", + "| loss_ent | 17.9 |\n", + "| ev_tdlam_before | -0.0046 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00479 |\n", + "| loss_pol_entpen | -0.179 |\n", + "| loss_vf_loss | 4.43e-10 |\n", + "| loss_kl | 0.000437 |\n", + "| loss_ent | 17.9 |\n", + "| ev_tdlam_before | -0.0457 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.179 |\n", + "| loss_vf_loss | 5.71e-10 |\n", + "| loss_kl | 0.000333 |\n", + "| loss_ent | 17.9 |\n", + "| ev_tdlam_before | -0.0496 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00487 |\n", + "| loss_pol_entpen | -0.179 |\n", + "| loss_vf_loss | 3.32e-09 |\n", + "| loss_kl | 0.000465 |\n", + "| loss_ent | 17.9 |\n", + "| ev_tdlam_before | -0.0242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00987 |\n", + "| loss_pol_entpen | -0.18 |\n", + "| loss_vf_loss | 7.71e-10 |\n", + "| loss_kl | 0.00116 |\n", + "| loss_ent | 18 |\n", + "| ev_tdlam_before | -0.0829 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 150 |\n", + "| TimestepsSoFar | 2.16e+05 |\n", + "| TimeElapsed | 1.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00767 |\n", + "| loss_pol_entpen | -0.18 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 0.000917 |\n", + "| loss_ent | 18 |\n", + "| ev_tdlam_before | 0.000954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00451 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 4.19e-11 |\n", + "| loss_kl | 0.00075 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.0464 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.17e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00499 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 0.000722 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.00904 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 1.49e-09 |\n", + "| loss_kl | 0.000304 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.00852 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00804 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 2.46e-09 |\n", + "| loss_kl | 0.000939 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.27 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.18 |\n", + "| loss_vf_loss | 2.1e-09 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 18 |\n", + "| ev_tdlam_before | -0.0474 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 152 |\n", + "| TimestepsSoFar | 2.19e+05 |\n", + "| TimeElapsed | 1.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0071 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 3.35e-09 |\n", + "| loss_kl | 0.000755 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 154 |\n", + "| TimestepsSoFar | 2.22e+05 |\n", + "| TimeElapsed | 1.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00468 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 0.000581 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.088 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 154 |\n", + "| TimestepsSoFar | 2.22e+05 |\n", + "| TimeElapsed | 1.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00439 |\n", + "| loss_pol_entpen | -0.181 |\n", + "| loss_vf_loss | 4.68e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 18.1 |\n", + "| ev_tdlam_before | -0.102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 154 |\n", + "| TimestepsSoFar | 2.22e+05 |\n", + "| TimeElapsed | 1.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.182 |\n", + "| loss_vf_loss | 9.13e-11 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 18.2 |\n", + "| ev_tdlam_before | 0.00584 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 154 |\n", + "| TimestepsSoFar | 2.22e+05 |\n", + "| TimeElapsed | 1.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.182 |\n", + "| loss_vf_loss | 3.04e-10 |\n", + "| loss_kl | 0.000268 |\n", + "| loss_ent | 18.2 |\n", + "| ev_tdlam_before | -0.00571 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 154 |\n", + "| TimestepsSoFar | 2.22e+05 |\n", + "| TimeElapsed | 1.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00982 |\n", + "| loss_pol_entpen | -0.183 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.00124 |\n", + "| loss_ent | 18.3 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00626 |\n", + "| loss_pol_entpen | -0.184 |\n", + "| loss_vf_loss | 2.66e-10 |\n", + "| loss_kl | 0.000922 |\n", + "| loss_ent | 18.4 |\n", + "| ev_tdlam_before | -0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.183 |\n", + "| loss_vf_loss | 3.32e-09 |\n", + "| loss_kl | 0.000355 |\n", + "| loss_ent | 18.3 |\n", + "| ev_tdlam_before | 0.0054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0056 |\n", + "| loss_pol_entpen | -0.184 |\n", + "| loss_vf_loss | 4.38e-09 |\n", + "| loss_kl | 0.000381 |\n", + "| loss_ent | 18.4 |\n", + "| ev_tdlam_before | -0.137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00381 |\n", + "| loss_pol_entpen | -0.184 |\n", + "| loss_vf_loss | 6e-10 |\n", + "| loss_kl | 0.000729 |\n", + "| loss_ent | 18.4 |\n", + "| ev_tdlam_before | -0.0626 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.184 |\n", + "| loss_vf_loss | 2.86e-10 |\n", + "| loss_kl | 0.000282 |\n", + "| loss_ent | 18.4 |\n", + "| ev_tdlam_before | -0.0249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 156 |\n", + "| TimestepsSoFar | 2.25e+05 |\n", + "| TimeElapsed | 1.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00769 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 3.63e-10 |\n", + "| loss_kl | 0.000791 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | 0.000245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.22e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 1.47e-09 |\n", + "| loss_kl | 0.000409 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | -0.000721 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 0.000409 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00905 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 6.54e-10 |\n", + "| loss_kl | 0.000851 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | -0.00164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.22e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00768 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 2.95e-09 |\n", + "| loss_kl | 0.00125 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | -0.0523 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00335 |\n", + "| loss_pol_entpen | -0.185 |\n", + "| loss_vf_loss | 3.47e-09 |\n", + "| loss_kl | 0.000362 |\n", + "| loss_ent | 18.5 |\n", + "| ev_tdlam_before | -0.0517 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 158 |\n", + "| TimestepsSoFar | 2.28e+05 |\n", + "| TimeElapsed | 1.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00916 |\n", + "| loss_pol_entpen | -0.186 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 0.00101 |\n", + "| loss_ent | 18.6 |\n", + "| ev_tdlam_before | -0.00692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0111 |\n", + "| loss_pol_entpen | -0.186 |\n", + "| loss_vf_loss | 4.63e-10 |\n", + "| loss_kl | 0.00144 |\n", + "| loss_ent | 18.6 |\n", + "| ev_tdlam_before | 0.00148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.186 |\n", + "| loss_vf_loss | 3.91e-10 |\n", + "| loss_kl | 0.000406 |\n", + "| loss_ent | 18.6 |\n", + "| ev_tdlam_before | -0.000965 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.24e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00296 |\n", + "| loss_pol_entpen | -0.186 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 0.000222 |\n", + "| loss_ent | 18.6 |\n", + "| ev_tdlam_before | 0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.004 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 5.93e-11 |\n", + "| loss_kl | 0.000542 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.0164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00764 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 2.72e-09 |\n", + "| loss_kl | 0.00086 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | 0.000567 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 160 |\n", + "| TimestepsSoFar | 2.3e+05 |\n", + "| TimeElapsed | 1.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00809 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 3.72e-10 |\n", + "| loss_kl | 0.00094 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.00111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 162 |\n", + "| TimestepsSoFar | 2.33e+05 |\n", + "| TimeElapsed | 1.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.29e-05 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 3.27e-11 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 162 |\n", + "| TimestepsSoFar | 2.33e+05 |\n", + "| TimeElapsed | 1.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 6.61e-11 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0683 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 162 |\n", + "| TimestepsSoFar | 2.33e+05 |\n", + "| TimeElapsed | 1.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 0.000222 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.00426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 162 |\n", + "| TimestepsSoFar | 2.33e+05 |\n", + "| TimeElapsed | 1.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 1.15e-09 |\n", + "| loss_kl | 0.000337 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.037 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 162 |\n", + "| TimestepsSoFar | 2.33e+05 |\n", + "| TimeElapsed | 1.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00601 |\n", + "| loss_pol_entpen | -0.189 |\n", + "| loss_vf_loss | 6.76e-10 |\n", + "| loss_kl | 0.000587 |\n", + "| loss_ent | 18.9 |\n", + "| ev_tdlam_before | -0.0315 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00303 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 2.37e-10 |\n", + "| loss_kl | 0.00038 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00353 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 0.000382 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 2.89e-10 |\n", + "| loss_kl | 0.000506 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00721 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 4.97e-10 |\n", + "| loss_kl | 0.000831 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | 0.00243 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00486 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 1.55e-09 |\n", + "| loss_kl | 0.000638 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | 0.000432 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 164 |\n", + "| TimestepsSoFar | 2.36e+05 |\n", + "| TimeElapsed | 1.27e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.186 |\n", + "| loss_vf_loss | 7.68e-10 |\n", + "| loss_kl | 0.000508 |\n", + "| loss_ent | 18.6 |\n", + "| ev_tdlam_before | -0.00288 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00429 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 0.000458 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.0588 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.28e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 1.91e-09 |\n", + "| loss_kl | 0.000568 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.000859 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.28e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00348 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 9.34e-11 |\n", + "| loss_kl | 0.00046 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00786 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 0.000681 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.00108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0111 |\n", + "| loss_pol_entpen | -0.187 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 0.00147 |\n", + "| loss_ent | 18.7 |\n", + "| ev_tdlam_before | -0.00785 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 166 |\n", + "| TimestepsSoFar | 2.39e+05 |\n", + "| TimeElapsed | 1.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 3.6e-10 |\n", + "| loss_kl | 0.000452 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | -0.0371 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00525 |\n", + "| loss_pol_entpen | -0.188 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 0.00056 |\n", + "| loss_ent | 18.8 |\n", + "| ev_tdlam_before | 0.00914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00428 |\n", + "| loss_pol_entpen | -0.189 |\n", + "| loss_vf_loss | 9.06e-10 |\n", + "| loss_kl | 0.0006 |\n", + "| loss_ent | 18.9 |\n", + "| ev_tdlam_before | -0.00246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00727 |\n", + "| loss_pol_entpen | -0.189 |\n", + "| loss_vf_loss | 2.15e-09 |\n", + "| loss_kl | 0.00101 |\n", + "| loss_ent | 18.9 |\n", + "| ev_tdlam_before | -0.0357 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0103 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 2.48e-09 |\n", + "| loss_kl | 0.00134 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0049 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 4.06e-09 |\n", + "| loss_kl | 0.000977 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.0997 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 168 |\n", + "| TimestepsSoFar | 2.42e+05 |\n", + "| TimeElapsed | 1.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 2.66e-09 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.0078 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 170 |\n", + "| TimestepsSoFar | 2.45e+05 |\n", + "| TimeElapsed | 1.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00446 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000424 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.0465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 170 |\n", + "| TimestepsSoFar | 2.45e+05 |\n", + "| TimeElapsed | 1.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000441 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.0351 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 170 |\n", + "| TimestepsSoFar | 2.45e+05 |\n", + "| TimeElapsed | 1.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00345 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | 0.0074 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 170 |\n", + "| TimestepsSoFar | 2.45e+05 |\n", + "| TimeElapsed | 1.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00249 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 0.000398 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.0059 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 170 |\n", + "| TimestepsSoFar | 2.45e+05 |\n", + "| TimeElapsed | 1.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00296 |\n", + "| loss_pol_entpen | -0.19 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 19 |\n", + "| ev_tdlam_before | -0.00367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0102 |\n", + "| loss_pol_entpen | -0.191 |\n", + "| loss_vf_loss | 7.27e-10 |\n", + "| loss_kl | 0.00123 |\n", + "| loss_ent | 19.1 |\n", + "| ev_tdlam_before | -0.0338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00701 |\n", + "| loss_pol_entpen | -0.191 |\n", + "| loss_vf_loss | 7.52e-11 |\n", + "| loss_kl | 0.00114 |\n", + "| loss_ent | 19.1 |\n", + "| ev_tdlam_before | -0.0467 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00397 |\n", + "| loss_pol_entpen | -0.191 |\n", + "| loss_vf_loss | 4.82e-10 |\n", + "| loss_kl | 0.000703 |\n", + "| loss_ent | 19.1 |\n", + "| ev_tdlam_before | 0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00778 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 6.23e-10 |\n", + "| loss_kl | 0.000875 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.000322 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00447 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 4.87e-10 |\n", + "| loss_kl | 0.000797 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.0858 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 172 |\n", + "| TimestepsSoFar | 2.48e+05 |\n", + "| TimeElapsed | 1.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000788 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 5.32e-05 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.000504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.34e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00864 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 0.00071 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.0348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 6.29e-10 |\n", + "| loss_kl | 0.000605 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.00472 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00248 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 1.98e-09 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00436 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 3.77e-10 |\n", + "| loss_kl | 0.000344 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | 0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 174 |\n", + "| TimestepsSoFar | 2.51e+05 |\n", + "| TimeElapsed | 1.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 2.35e-10 |\n", + "| loss_kl | 0.000302 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | 0.0252 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00642 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 5.64e-10 |\n", + "| loss_kl | 0.000635 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | 0.00102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0123 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 3.93e-10 |\n", + "| loss_kl | 0.00155 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.00966 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00605 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 9.21e-10 |\n", + "| loss_kl | 0.00105 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.0206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000586 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 2.23e-09 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.00463 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00407 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 0.000373 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.00986 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 176 |\n", + "| TimestepsSoFar | 2.53e+05 |\n", + "| TimeElapsed | 1.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00495 |\n", + "| loss_pol_entpen | -0.192 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 19.2 |\n", + "| ev_tdlam_before | -0.236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 178 |\n", + "| TimestepsSoFar | 2.56e+05 |\n", + "| TimeElapsed | 1.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00439 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 3.03e-09 |\n", + "| loss_kl | 0.000423 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | -0.00799 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 178 |\n", + "| TimestepsSoFar | 2.56e+05 |\n", + "| TimeElapsed | 1.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 5.88e-09 |\n", + "| loss_kl | 0.000517 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 178 |\n", + "| TimestepsSoFar | 2.56e+05 |\n", + "| TimeElapsed | 1.37e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00675 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 3.29e-09 |\n", + "| loss_kl | 0.000601 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | -0.302 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 178 |\n", + "| TimestepsSoFar | 2.56e+05 |\n", + "| TimeElapsed | 1.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00607 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 1.73e-09 |\n", + "| loss_kl | 0.000832 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.0114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 178 |\n", + "| TimestepsSoFar | 2.56e+05 |\n", + "| TimeElapsed | 1.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00446 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000718 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.000735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000424 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | -0.00492 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 8.72e-11 |\n", + "| loss_kl | 0.000199 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00651 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 6.44e-10 |\n", + "| loss_kl | 0.000811 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.00205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00421 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 5.74e-11 |\n", + "| loss_kl | 0.000597 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00152 |\n", + "| loss_pol_entpen | -0.193 |\n", + "| loss_vf_loss | 3.2e-10 |\n", + "| loss_kl | 0.00028 |\n", + "| loss_ent | 19.3 |\n", + "| ev_tdlam_before | 0.00303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 180 |\n", + "| TimestepsSoFar | 2.59e+05 |\n", + "| TimeElapsed | 1.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 2.03e-10 |\n", + "| loss_kl | 0.000261 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.00931 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 3.4e-10 |\n", + "| loss_kl | 0.000258 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0125 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 9.44e-10 |\n", + "| loss_kl | 0.00116 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00553 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 0.00106 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.0302 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00461 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 4.47e-10 |\n", + "| loss_kl | 0.000664 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | 0.00227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00682 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 1.56e-09 |\n", + "| loss_kl | 0.000619 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | 0.00829 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 182 |\n", + "| TimestepsSoFar | 2.62e+05 |\n", + "| TimeElapsed | 1.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 7.53e-10 |\n", + "| loss_kl | 0.000444 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | 0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00662 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000837 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 1.5e-09 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.0353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00525 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 4.97e-10 |\n", + "| loss_kl | 0.000562 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00699 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 2.79e-11 |\n", + "| loss_kl | 0.000783 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.194 |\n", + "| loss_vf_loss | 9.09e-11 |\n", + "| loss_kl | 0.000406 |\n", + "| loss_ent | 19.4 |\n", + "| ev_tdlam_before | -0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 184 |\n", + "| TimestepsSoFar | 2.65e+05 |\n", + "| TimeElapsed | 1.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00519 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 4.27e-10 |\n", + "| loss_kl | 0.000415 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.000864 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 186 |\n", + "| TimestepsSoFar | 2.68e+05 |\n", + "| TimeElapsed | 1.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 1.35e-09 |\n", + "| loss_kl | 0.000283 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.0504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 186 |\n", + "| TimestepsSoFar | 2.68e+05 |\n", + "| TimeElapsed | 1.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 3.32e-09 |\n", + "| loss_kl | 0.000225 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.088 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 186 |\n", + "| TimestepsSoFar | 2.68e+05 |\n", + "| TimeElapsed | 1.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0068 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 6.05e-09 |\n", + "| loss_kl | 0.000596 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 186 |\n", + "| TimestepsSoFar | 2.68e+05 |\n", + "| TimeElapsed | 1.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00823 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 1.09e-09 |\n", + "| loss_kl | 0.00111 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | -0.0657 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 186 |\n", + "| TimestepsSoFar | 2.68e+05 |\n", + "| TimeElapsed | 1.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00408 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 4.25e-10 |\n", + "| loss_kl | 0.000478 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | -0.119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00434 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 3.47e-10 |\n", + "| loss_kl | 0.000371 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | -0.000333 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0117 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 1.18e-09 |\n", + "| loss_kl | 0.000891 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | -0.0581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00489 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 0.000827 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.00275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00511 |\n", + "| loss_pol_entpen | -0.195 |\n", + "| loss_vf_loss | 2.81e-09 |\n", + "| loss_kl | 0.000512 |\n", + "| loss_ent | 19.5 |\n", + "| ev_tdlam_before | -0.00011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000289 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 188 |\n", + "| TimestepsSoFar | 2.71e+05 |\n", + "| TimeElapsed | 1.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.196 |\n", + "| loss_vf_loss | 6.56e-11 |\n", + "| loss_kl | 0.000318 |\n", + "| loss_ent | 19.6 |\n", + "| ev_tdlam_before | 0.00109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00533 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000657 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | 0.00217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 7.84e-10 |\n", + "| loss_kl | 0.000209 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -0.0956 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | 0.00908 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 1.9e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -0.0809 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.47e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000627 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 9.67e-05 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -7.87e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 190 |\n", + "| TimestepsSoFar | 2.74e+05 |\n", + "| TimeElapsed | 1.47e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0077 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 7.64e-10 |\n", + "| loss_kl | 0.000748 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -0.00643 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00443 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 0.000574 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -0.0537 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00438 |\n", + "| loss_pol_entpen | -0.197 |\n", + "| loss_vf_loss | 3.51e-10 |\n", + "| loss_kl | 0.00037 |\n", + "| loss_ent | 19.7 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00521 |\n", + "| loss_pol_entpen | -0.198 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 0.00087 |\n", + "| loss_ent | 19.8 |\n", + "| ev_tdlam_before | -0.019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00589 |\n", + "| loss_pol_entpen | -0.198 |\n", + "| loss_vf_loss | 5.11e-11 |\n", + "| loss_kl | 0.000695 |\n", + "| loss_ent | 19.8 |\n", + "| ev_tdlam_before | -0.00712 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.198 |\n", + "| loss_vf_loss | 6.67e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 19.8 |\n", + "| ev_tdlam_before | -0.000993 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 192 |\n", + "| TimestepsSoFar | 2.76e+05 |\n", + "| TimeElapsed | 1.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0061 |\n", + "| loss_pol_entpen | -0.199 |\n", + "| loss_vf_loss | 1.33e-09 |\n", + "| loss_kl | 0.000767 |\n", + "| loss_ent | 19.9 |\n", + "| ev_tdlam_before | -0.00804 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 194 |\n", + "| TimestepsSoFar | 2.79e+05 |\n", + "| TimeElapsed | 1.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00785 |\n", + "| loss_pol_entpen | -0.199 |\n", + "| loss_vf_loss | 9.87e-10 |\n", + "| loss_kl | 0.000585 |\n", + "| loss_ent | 19.9 |\n", + "| ev_tdlam_before | -0.0627 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 194 |\n", + "| TimestepsSoFar | 2.79e+05 |\n", + "| TimeElapsed | 1.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00216 |\n", + "| loss_pol_entpen | -0.199 |\n", + "| loss_vf_loss | 2.2e-09 |\n", + "| loss_kl | 0.000531 |\n", + "| loss_ent | 19.9 |\n", + "| ev_tdlam_before | -0.0235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 194 |\n", + "| TimestepsSoFar | 2.79e+05 |\n", + "| TimeElapsed | 1.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00774 |\n", + "| loss_pol_entpen | -0.199 |\n", + "| loss_vf_loss | 4.13e-09 |\n", + "| loss_kl | 0.00061 |\n", + "| loss_ent | 19.9 |\n", + "| ev_tdlam_before | -0.185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 194 |\n", + "| TimestepsSoFar | 2.79e+05 |\n", + "| TimeElapsed | 1.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00504 |\n", + "| loss_pol_entpen | -0.2 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 0.000791 |\n", + "| loss_ent | 20 |\n", + "| ev_tdlam_before | -0.214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 194 |\n", + "| TimestepsSoFar | 2.79e+05 |\n", + "| TimeElapsed | 1.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 2.94e-10 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.0086 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.51e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 3.23e-10 |\n", + "| loss_kl | 9.69e-05 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.000643 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00426 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000307 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | 0.00944 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 3.08e-10 |\n", + "| loss_kl | 0.000302 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.00864 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 5.24e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.00979 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00403 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 7.85e-10 |\n", + "| loss_kl | 0.000392 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | 0.0109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 196 |\n", + "| TimestepsSoFar | 2.82e+05 |\n", + "| TimeElapsed | 1.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00532 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 4.41e-10 |\n", + "| loss_kl | 0.000501 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | 0.00637 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.0263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.2 |\n", + "| loss_vf_loss | 5.98e-11 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 20 |\n", + "| ev_tdlam_before | 0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.53e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.2 |\n", + "| loss_vf_loss | 9.73e-10 |\n", + "| loss_kl | 0.0002 |\n", + "| loss_ent | 20 |\n", + "| ev_tdlam_before | -0.00397 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00729 |\n", + "| loss_pol_entpen | -0.2 |\n", + "| loss_vf_loss | 1.31e-09 |\n", + "| loss_kl | 0.000852 |\n", + "| loss_ent | 20 |\n", + "| ev_tdlam_before | -0.083 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.201 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 0.000331 |\n", + "| loss_ent | 20.1 |\n", + "| ev_tdlam_before | -0.0621 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 198 |\n", + "| TimestepsSoFar | 2.85e+05 |\n", + "| TimeElapsed | 1.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 3.04e-09 |\n", + "| loss_kl | 0.000512 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.00883 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 6.02e-09 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00505 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 3.26e-09 |\n", + "| loss_kl | 0.000377 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00612 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 4.12e-10 |\n", + "| loss_kl | 0.000842 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 3.2e-09 |\n", + "| loss_kl | 0.000189 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.00505 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 1.05e-09 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.0626 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 200 |\n", + "| TimestepsSoFar | 2.88e+05 |\n", + "| TimeElapsed | 1.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00857 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.22e-09 |\n", + "| loss_kl | 0.00103 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.00465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 202 |\n", + "| TimestepsSoFar | 2.91e+05 |\n", + "| TimeElapsed | 1.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00618 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000885 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.0563 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 202 |\n", + "| TimestepsSoFar | 2.91e+05 |\n", + "| TimeElapsed | 1.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00306 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 2.44e-10 |\n", + "| loss_kl | 0.000377 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.00548 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 202 |\n", + "| TimestepsSoFar | 2.91e+05 |\n", + "| TimeElapsed | 1.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.0142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 202 |\n", + "| TimestepsSoFar | 2.91e+05 |\n", + "| TimeElapsed | 1.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00742 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 0.000742 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | 0.00361 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 202 |\n", + "| TimestepsSoFar | 2.91e+05 |\n", + "| TimeElapsed | 1.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00874 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 0.000883 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.0275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.005 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000849 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00392 |\n", + "| loss_pol_entpen | -0.203 |\n", + "| loss_vf_loss | 1.45e-09 |\n", + "| loss_kl | 0.000389 |\n", + "| loss_ent | 20.3 |\n", + "| ev_tdlam_before | -0.0809 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00438 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 1.56e-09 |\n", + "| loss_kl | 0.000452 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.0851 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0048 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 1.5e-09 |\n", + "| loss_kl | 0.000565 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.57e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00513 |\n", + "| loss_pol_entpen | -0.202 |\n", + "| loss_vf_loss | 3.84e-10 |\n", + "| loss_kl | 0.000339 |\n", + "| loss_ent | 20.2 |\n", + "| ev_tdlam_before | -0.0408 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 204 |\n", + "| TimestepsSoFar | 2.94e+05 |\n", + "| TimeElapsed | 1.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00087 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 7.62e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.00193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 8.6e-10 |\n", + "| loss_kl | 0.000158 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.0707 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00433 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 1.3e-09 |\n", + "| loss_kl | 0.000438 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.0591 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00287 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 7.86e-10 |\n", + "| loss_kl | 0.00031 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00364 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00152 |\n", + "| loss_pol_entpen | -0.204 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 0.000139 |\n", + "| loss_ent | 20.4 |\n", + "| ev_tdlam_before | 0.00735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 206 |\n", + "| TimestepsSoFar | 2.97e+05 |\n", + "| TimeElapsed | 1.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00718 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 4.27e-10 |\n", + "| loss_kl | 0.000616 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | 0.00019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00419 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.00058 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | -0.00655 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00249 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 2.13e-09 |\n", + "| loss_kl | 0.000429 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00666 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 0.000604 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | -0.0218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00524 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 2.81e-09 |\n", + "| loss_kl | 0.000645 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | -0.0338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.205 |\n", + "| loss_vf_loss | 7.31e-11 |\n", + "| loss_kl | 0.000337 |\n", + "| loss_ent | 20.5 |\n", + "| ev_tdlam_before | -0.093 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 208 |\n", + "| TimestepsSoFar | 3e+05 |\n", + "| TimeElapsed | 1.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00722 |\n", + "| loss_pol_entpen | -0.207 |\n", + "| loss_vf_loss | 5.67e-11 |\n", + "| loss_kl | 0.000948 |\n", + "| loss_ent | 20.7 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 210 |\n", + "| TimestepsSoFar | 3.02e+05 |\n", + "| TimeElapsed | 1.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.207 |\n", + "| loss_vf_loss | 3.33e-10 |\n", + "| loss_kl | 0.00083 |\n", + "| loss_ent | 20.7 |\n", + "| ev_tdlam_before | 0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 210 |\n", + "| TimestepsSoFar | 3.02e+05 |\n", + "| TimeElapsed | 1.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00543 |\n", + "| loss_pol_entpen | -0.207 |\n", + "| loss_vf_loss | 9.67e-11 |\n", + "| loss_kl | 0.000798 |\n", + "| loss_ent | 20.7 |\n", + "| ev_tdlam_before | 0.00702 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 210 |\n", + "| TimestepsSoFar | 3.02e+05 |\n", + "| TimeElapsed | 1.62e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00417 |\n", + "| loss_pol_entpen | -0.208 |\n", + "| loss_vf_loss | 6e-10 |\n", + "| loss_kl | 0.000745 |\n", + "| loss_ent | 20.8 |\n", + "| ev_tdlam_before | -0.000927 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 210 |\n", + "| TimestepsSoFar | 3.02e+05 |\n", + "| TimeElapsed | 1.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000989 |\n", + "| loss_pol_entpen | -0.208 |\n", + "| loss_vf_loss | 5.75e-11 |\n", + "| loss_kl | 0.000214 |\n", + "| loss_ent | 20.8 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 210 |\n", + "| TimestepsSoFar | 3.02e+05 |\n", + "| TimeElapsed | 1.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00609 |\n", + "| loss_pol_entpen | -0.209 |\n", + "| loss_vf_loss | 3.23e-10 |\n", + "| loss_kl | 0.000778 |\n", + "| loss_ent | 20.9 |\n", + "| ev_tdlam_before | -0.00815 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.63e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00643 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000883 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.0142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0027 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 0.000508 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00666 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 8.49e-10 |\n", + "| loss_kl | 0.000487 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | 0.00299 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000853 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | 0.00436 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00434 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 7.98e-10 |\n", + "| loss_kl | 0.00052 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.00364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 212 |\n", + "| TimestepsSoFar | 3.05e+05 |\n", + "| TimeElapsed | 1.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00437 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 7.12e-10 |\n", + "| loss_kl | 0.000411 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00278 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 0.000326 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.0224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 8.32e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.00151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00339 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 5.03e-09 |\n", + "| loss_kl | 0.000296 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.0216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 0.000213 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.21 |\n", + "| loss_vf_loss | 8.53e-09 |\n", + "| loss_kl | 0.000346 |\n", + "| loss_ent | 21 |\n", + "| ev_tdlam_before | -0.000366 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 214 |\n", + "| TimestepsSoFar | 3.08e+05 |\n", + "| TimeElapsed | 1.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00317 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000283 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 8.8e-11 |\n", + "| loss_kl | 0.000547 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | -0.102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00509 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 4.35e-10 |\n", + "| loss_kl | 0.000511 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | -0.0054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 2.74e-10 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | -0.0356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00588 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 1.59e-09 |\n", + "| loss_kl | 0.000745 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00207 |\n", + "| loss_pol_entpen | -0.211 |\n", + "| loss_vf_loss | 3.36e-10 |\n", + "| loss_kl | 0.000316 |\n", + "| loss_ent | 21.1 |\n", + "| ev_tdlam_before | 0.0162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 216 |\n", + "| TimestepsSoFar | 3.11e+05 |\n", + "| TimeElapsed | 1.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 2.82e-10 |\n", + "| loss_kl | 0.000695 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0386 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 218 |\n", + "| TimestepsSoFar | 3.14e+05 |\n", + "| TimeElapsed | 1.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 4.81e-11 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 218 |\n", + "| TimestepsSoFar | 3.14e+05 |\n", + "| TimeElapsed | 1.68e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00465 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 0.000623 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | 0.000558 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 218 |\n", + "| TimestepsSoFar | 3.14e+05 |\n", + "| TimeElapsed | 1.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00242 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 5.92e-11 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 218 |\n", + "| TimestepsSoFar | 3.14e+05 |\n", + "| TimeElapsed | 1.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00506 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.000443 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.00188 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 218 |\n", + "| TimestepsSoFar | 3.14e+05 |\n", + "| TimeElapsed | 1.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00745 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 3.26e-10 |\n", + "| loss_kl | 0.000624 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.00701 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00383 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 4.16e-10 |\n", + "| loss_kl | 0.000678 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00455 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 5.34e-10 |\n", + "| loss_kl | 0.000572 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00519 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 0.00049 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.7e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 5.36e-11 |\n", + "| loss_kl | 0.000355 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.000937 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00759 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1e-09 |\n", + "| loss_kl | 0.000846 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 220 |\n", + "| TimestepsSoFar | 3.17e+05 |\n", + "| TimeElapsed | 1.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00637 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000868 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.00252 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 0.000696 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | 0.00749 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00508 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.77e-09 |\n", + "| loss_kl | 0.000557 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.002 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 6.94e-10 |\n", + "| loss_kl | 0.000356 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.268 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 5.23e-09 |\n", + "| loss_kl | 0.000365 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | 0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00571 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 3.23e-09 |\n", + "| loss_kl | 0.000697 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | -0.4 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 222 |\n", + "| TimestepsSoFar | 3.2e+05 |\n", + "| TimeElapsed | 1.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 0.000393 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | 0.000617 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00295 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 4.96e-10 |\n", + "| loss_kl | 0.000276 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | -0.00331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0044 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000531 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | 0.000227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00453 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.46e-09 |\n", + "| loss_kl | 0.000534 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.73e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00035 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.23e-09 |\n", + "| loss_kl | 8.45e-05 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.0913 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00496 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000497 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.387 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 224 |\n", + "| TimestepsSoFar | 3.23e+05 |\n", + "| TimeElapsed | 1.73e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00575 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 5.75e-10 |\n", + "| loss_kl | 0.000515 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | -0.000468 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 226 |\n", + "| TimestepsSoFar | 3.25e+05 |\n", + "| TimeElapsed | 1.74e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00706 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 0.000917 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0347 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 226 |\n", + "| TimestepsSoFar | 3.25e+05 |\n", + "| TimeElapsed | 1.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 0.000308 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.063 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 226 |\n", + "| TimestepsSoFar | 3.25e+05 |\n", + "| TimeElapsed | 1.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00463 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.000496 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0058 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 226 |\n", + "| TimestepsSoFar | 3.25e+05 |\n", + "| TimeElapsed | 1.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0107 |\n", + "| loss_pol_entpen | -0.212 |\n", + "| loss_vf_loss | 7.54e-11 |\n", + "| loss_kl | 0.00112 |\n", + "| loss_ent | 21.2 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 226 |\n", + "| TimestepsSoFar | 3.25e+05 |\n", + "| TimeElapsed | 1.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00507 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 0.000773 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.000988 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00714 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 1.77e-09 |\n", + "| loss_kl | 0.000577 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.213 |\n", + "| loss_vf_loss | 2e-09 |\n", + "| loss_kl | 0.000375 |\n", + "| loss_ent | 21.3 |\n", + "| ev_tdlam_before | -0.0644 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00456 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 2.77e-10 |\n", + "| loss_kl | 0.00048 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.0848 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00243 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 0.000303 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | -0.000538 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.76e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0063 |\n", + "| loss_pol_entpen | -0.214 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 0.000577 |\n", + "| loss_ent | 21.4 |\n", + "| ev_tdlam_before | 0.00459 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 228 |\n", + "| TimestepsSoFar | 3.28e+05 |\n", + "| TimeElapsed | 1.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00239 |\n", + "| loss_pol_entpen | -0.215 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 21.5 |\n", + "| ev_tdlam_before | -0.00692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.215 |\n", + "| loss_vf_loss | 7.73e-11 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 21.5 |\n", + "| ev_tdlam_before | -0.0224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00116 |\n", + "| loss_pol_entpen | -0.215 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 21.5 |\n", + "| ev_tdlam_before | -0.0397 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00679 |\n", + "| loss_pol_entpen | -0.215 |\n", + "| loss_vf_loss | 4.18e-11 |\n", + "| loss_kl | 0.000674 |\n", + "| loss_ent | 21.5 |\n", + "| ev_tdlam_before | 0.00548 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00557 |\n", + "| loss_pol_entpen | -0.216 |\n", + "| loss_vf_loss | 5.61e-11 |\n", + "| loss_kl | 0.000822 |\n", + "| loss_ent | 21.6 |\n", + "| ev_tdlam_before | -0.000269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00345 |\n", + "| loss_pol_entpen | -0.216 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000579 |\n", + "| loss_ent | 21.6 |\n", + "| ev_tdlam_before | -0.00598 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 230 |\n", + "| TimestepsSoFar | 3.31e+05 |\n", + "| TimeElapsed | 1.77e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00404 |\n", + "| loss_pol_entpen | -0.217 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 21.7 |\n", + "| ev_tdlam_before | 0.0148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00348 |\n", + "| loss_pol_entpen | -0.217 |\n", + "| loss_vf_loss | 2.6e-10 |\n", + "| loss_kl | 0.000496 |\n", + "| loss_ent | 21.7 |\n", + "| ev_tdlam_before | -0.00855 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.78e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000656 |\n", + "| loss_pol_entpen | -0.218 |\n", + "| loss_vf_loss | 5.49e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 21.8 |\n", + "| ev_tdlam_before | -0.00313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.218 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.000323 |\n", + "| loss_ent | 21.8 |\n", + "| ev_tdlam_before | 0.000589 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.218 |\n", + "| loss_vf_loss | 7.77e-11 |\n", + "| loss_kl | 0.000558 |\n", + "| loss_ent | 21.8 |\n", + "| ev_tdlam_before | -0.0368 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00565 |\n", + "| loss_pol_entpen | -0.218 |\n", + "| loss_vf_loss | 8.3e-10 |\n", + "| loss_kl | 0.000592 |\n", + "| loss_ent | 21.8 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 232 |\n", + "| TimestepsSoFar | 3.34e+05 |\n", + "| TimeElapsed | 1.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0111 |\n", + "| loss_pol_entpen | -0.221 |\n", + "| loss_vf_loss | 1.16e-09 |\n", + "| loss_kl | 0.00124 |\n", + "| loss_ent | 22.1 |\n", + "| ev_tdlam_before | -0.00956 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 234 |\n", + "| TimestepsSoFar | 3.37e+05 |\n", + "| TimeElapsed | 1.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.221 |\n", + "| loss_vf_loss | 1.24e-09 |\n", + "| loss_kl | 0.000882 |\n", + "| loss_ent | 22.1 |\n", + "| ev_tdlam_before | -0.0653 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 234 |\n", + "| TimestepsSoFar | 3.37e+05 |\n", + "| TimeElapsed | 1.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 0.000179 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 234 |\n", + "| TimestepsSoFar | 3.37e+05 |\n", + "| TimeElapsed | 1.8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.221 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 22.1 |\n", + "| ev_tdlam_before | -0.000301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 234 |\n", + "| TimestepsSoFar | 3.37e+05 |\n", + "| TimeElapsed | 1.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00633 |\n", + "| loss_pol_entpen | -0.221 |\n", + "| loss_vf_loss | 6.27e-10 |\n", + "| loss_kl | 0.000618 |\n", + "| loss_ent | 22.1 |\n", + "| ev_tdlam_before | -0.00183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 234 |\n", + "| TimestepsSoFar | 3.37e+05 |\n", + "| TimeElapsed | 1.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00195 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000302 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | 0.000571 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00494 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000428 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0103 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 0.000723 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000731 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 8.82e-11 |\n", + "| loss_kl | 0.000497 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.00551 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.82e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00592 |\n", + "| loss_pol_entpen | -0.223 |\n", + "| loss_vf_loss | 6.9e-11 |\n", + "| loss_kl | 0.000466 |\n", + "| loss_ent | 22.3 |\n", + "| ev_tdlam_before | -0.00288 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00387 |\n", + "| loss_pol_entpen | -0.223 |\n", + "| loss_vf_loss | 3.6e-10 |\n", + "| loss_kl | 0.000645 |\n", + "| loss_ent | 22.3 |\n", + "| ev_tdlam_before | 5.86e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 236 |\n", + "| TimestepsSoFar | 3.4e+05 |\n", + "| TimeElapsed | 1.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00565 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 4.22e-09 |\n", + "| loss_kl | 0.000599 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.271 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000507 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.83e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00475 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 7.54e-10 |\n", + "| loss_kl | 0.000474 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00494 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000529 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | 0.00595 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | 0.00217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00368 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 1.93e-09 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 238 |\n", + "| TimestepsSoFar | 3.43e+05 |\n", + "| TimeElapsed | 1.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 7.99e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0312 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 6.85e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 2.3e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.00606 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.222 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 22.2 |\n", + "| ev_tdlam_before | -0.000665 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.223 |\n", + "| loss_vf_loss | 6.52e-10 |\n", + "| loss_kl | 0.000245 |\n", + "| loss_ent | 22.3 |\n", + "| ev_tdlam_before | 0.00128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00374 |\n", + "| loss_pol_entpen | -0.223 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.00048 |\n", + "| loss_ent | 22.3 |\n", + "| ev_tdlam_before | -0.00976 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 240 |\n", + "| TimestepsSoFar | 3.46e+05 |\n", + "| TimeElapsed | 1.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00913 |\n", + "| loss_pol_entpen | -0.223 |\n", + "| loss_vf_loss | 6e-10 |\n", + "| loss_kl | 0.000765 |\n", + "| loss_ent | 22.3 |\n", + "| ev_tdlam_before | -0.00247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 242 |\n", + "| TimestepsSoFar | 3.48e+05 |\n", + "| TimeElapsed | 1.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 9.71e-10 |\n", + "| loss_kl | 0.000367 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.0338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 242 |\n", + "| TimestepsSoFar | 3.48e+05 |\n", + "| TimeElapsed | 1.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0098 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 2.61e-09 |\n", + "| loss_kl | 0.00123 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 242 |\n", + "| TimestepsSoFar | 3.48e+05 |\n", + "| TimeElapsed | 1.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00342 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 4.52e-10 |\n", + "| loss_kl | 0.000636 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.0598 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 242 |\n", + "| TimestepsSoFar | 3.48e+05 |\n", + "| TimeElapsed | 1.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0088 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 5.28e-10 |\n", + "| loss_kl | 0.000995 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.00239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 242 |\n", + "| TimestepsSoFar | 3.48e+05 |\n", + "| TimeElapsed | 1.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00994 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 2.94e-10 |\n", + "| loss_kl | 0.000959 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00396 |\n", + "| loss_pol_entpen | -0.224 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 0.000721 |\n", + "| loss_ent | 22.4 |\n", + "| ev_tdlam_before | -0.00822 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00473 |\n", + "| loss_pol_entpen | -0.225 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 22.5 |\n", + "| ev_tdlam_before | -0.0551 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00462 |\n", + "| loss_pol_entpen | -0.225 |\n", + "| loss_vf_loss | 5.73e-11 |\n", + "| loss_kl | 0.000695 |\n", + "| loss_ent | 22.5 |\n", + "| ev_tdlam_before | -0.199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.88e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00567 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 4.92e-10 |\n", + "| loss_kl | 0.000717 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | 0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00181 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 6.46e-11 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | -0.0214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000272 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 244 |\n", + "| TimestepsSoFar | 3.51e+05 |\n", + "| TimeElapsed | 1.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | -0.00527 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 4.36e-10 |\n", + "| loss_kl | 0.000247 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | -0.014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | 0.00236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00497 |\n", + "| loss_pol_entpen | -0.226 |\n", + "| loss_vf_loss | 3.58e-10 |\n", + "| loss_kl | 0.000336 |\n", + "| loss_ent | 22.6 |\n", + "| ev_tdlam_before | 0.000392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00339 |\n", + "| loss_pol_entpen | -0.225 |\n", + "| loss_vf_loss | 9.37e-11 |\n", + "| loss_kl | 0.000475 |\n", + "| loss_ent | 22.5 |\n", + "| ev_tdlam_before | -0.0262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00845 |\n", + "| loss_pol_entpen | -0.225 |\n", + "| loss_vf_loss | 4.61e-10 |\n", + "| loss_kl | 0.000931 |\n", + "| loss_ent | 22.5 |\n", + "| ev_tdlam_before | -0.0318 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 246 |\n", + "| TimestepsSoFar | 3.54e+05 |\n", + "| TimeElapsed | 1.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 4.3e-09 |\n", + "| loss_kl | 0.000764 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | -0.0107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00242 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 8.54e-10 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 4.05e-10 |\n", + "| loss_kl | 0.00021 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | -0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0051 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.000411 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | 0.000456 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00279 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 7.33e-11 |\n", + "| loss_kl | 0.00032 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | -0.0289 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.227 |\n", + "| loss_vf_loss | 1.94e-09 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 22.7 |\n", + "| ev_tdlam_before | -0.0845 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 248 |\n", + "| TimestepsSoFar | 3.57e+05 |\n", + "| TimeElapsed | 1.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 3.65e-10 |\n", + "| loss_kl | 0.000273 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | 0.00616 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00027 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 250 |\n", + "| TimestepsSoFar | 3.6e+05 |\n", + "| TimeElapsed | 1.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 6.79e-11 |\n", + "| loss_kl | 0.000352 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | 0.0147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00027 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 250 |\n", + "| TimestepsSoFar | 3.6e+05 |\n", + "| TimeElapsed | 1.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0043 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 1.59e-09 |\n", + "| loss_kl | 0.000524 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.00176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00027 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 250 |\n", + "| TimestepsSoFar | 3.6e+05 |\n", + "| TimeElapsed | 1.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00304 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 3.31e-10 |\n", + "| loss_kl | 0.000435 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.0661 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00027 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 250 |\n", + "| TimestepsSoFar | 3.6e+05 |\n", + "| TimeElapsed | 1.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 1.68e-09 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | 0.019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00027 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 250 |\n", + "| TimestepsSoFar | 3.6e+05 |\n", + "| TimeElapsed | 1.93e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00524 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 0.000791 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.0326 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0.000337 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 0.000359 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | 0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00768 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 3.78e-10 |\n", + "| loss_kl | 0.000893 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | 0.00316 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00815 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 9.32e-10 |\n", + "| loss_kl | 0.00111 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.0201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 8.93e-10 |\n", + "| loss_kl | 0.000281 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.00601 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 252 |\n", + "| TimestepsSoFar | 3.63e+05 |\n", + "| TimeElapsed | 1.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 8.95e-11 |\n", + "| loss_kl | 0.000374 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00559 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 9.1e-11 |\n", + "| loss_kl | 0.000539 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.00416 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 9.24e-10 |\n", + "| loss_kl | 0.000475 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.00184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 0.000269 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.0188 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.229 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 22.9 |\n", + "| ev_tdlam_before | -0.0378 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 254 |\n", + "| TimestepsSoFar | 3.66e+05 |\n", + "| TimeElapsed | 1.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 4e-10 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.0663 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 7.48e-10 |\n", + "| loss_kl | 0.000272 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.00932 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0088 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 8.13e-10 |\n", + "| loss_kl | 0.000823 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000214 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.00377 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0105 |\n", + "| loss_pol_entpen | -0.23 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.00106 |\n", + "| loss_ent | 23 |\n", + "| ev_tdlam_before | -0.0828 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00286 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 0.000611 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | 0.00458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 256 |\n", + "| TimestepsSoFar | 3.69e+05 |\n", + "| TimeElapsed | 1.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 3.34e-10 |\n", + "| loss_kl | 0.000519 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.0249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 258 |\n", + "| TimestepsSoFar | 3.72e+05 |\n", + "| TimeElapsed | 1.98e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0032 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.000518 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.0106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 258 |\n", + "| TimestepsSoFar | 3.72e+05 |\n", + "| TimeElapsed | 1.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.00027 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.00965 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 258 |\n", + "| TimestepsSoFar | 3.72e+05 |\n", + "| TimeElapsed | 1.98e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00452 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 8.62e-10 |\n", + "| loss_kl | 0.000465 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.000556 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 258 |\n", + "| TimestepsSoFar | 3.72e+05 |\n", + "| TimeElapsed | 1.99e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.231 |\n", + "| loss_vf_loss | 2.9e-09 |\n", + "| loss_kl | 0.000418 |\n", + "| loss_ent | 23.1 |\n", + "| ev_tdlam_before | -0.0711 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 258 |\n", + "| TimestepsSoFar | 3.72e+05 |\n", + "| TimeElapsed | 1.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 1.04e-09 |\n", + "| loss_kl | 0.000302 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | 7.08e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00214 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 1.31e-09 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 8.78e-11 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.0855 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 1.43e-09 |\n", + "| loss_kl | 0.000272 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | 0.00242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.0455 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 3.65e-10 |\n", + "| loss_kl | 0.000145 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.0175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 260 |\n", + "| TimestepsSoFar | 3.74e+05 |\n", + "| TimeElapsed | 2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00366 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 3.1e-10 |\n", + "| loss_kl | 0.000484 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00412 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 7.08e-10 |\n", + "| loss_kl | 0.000459 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | 0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00549 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 2.91e-10 |\n", + "| loss_kl | 0.000605 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.0256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00541 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 1.04e-09 |\n", + "| loss_kl | 0.000802 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | 0.000442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0111 |\n", + "| loss_pol_entpen | -0.232 |\n", + "| loss_vf_loss | 8.21e-10 |\n", + "| loss_kl | 0.00131 |\n", + "| loss_ent | 23.2 |\n", + "| ev_tdlam_before | -0.0327 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00622 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 1.17e-09 |\n", + "| loss_kl | 0.000872 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0221 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 262 |\n", + "| TimestepsSoFar | 3.77e+05 |\n", + "| TimeElapsed | 2.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 2.74e-09 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 4.81e-09 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0532 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0051 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 6.23e-09 |\n", + "| loss_kl | 0.000563 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00578 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 2.61e-09 |\n", + "| loss_kl | 0.000745 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00979 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 0.000701 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.333 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00207 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 4.79e-10 |\n", + "| loss_kl | 0.000525 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.00695 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 264 |\n", + "| TimestepsSoFar | 3.8e+05 |\n", + "| TimeElapsed | 2.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00245 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 9.88e-10 |\n", + "| loss_kl | 0.000269 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 266 |\n", + "| TimestepsSoFar | 3.83e+05 |\n", + "| TimeElapsed | 2.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0057 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 3.17e-10 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0566 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 266 |\n", + "| TimestepsSoFar | 3.83e+05 |\n", + "| TimeElapsed | 2.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00471 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 4.56e-10 |\n", + "| loss_kl | 0.000567 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0417 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 266 |\n", + "| TimestepsSoFar | 3.83e+05 |\n", + "| TimeElapsed | 2.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0104 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 0.00118 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 266 |\n", + "| TimestepsSoFar | 3.83e+05 |\n", + "| TimeElapsed | 2.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.233 |\n", + "| loss_vf_loss | 4.32e-11 |\n", + "| loss_kl | 0.00046 |\n", + "| loss_ent | 23.3 |\n", + "| ev_tdlam_before | 0.00554 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 266 |\n", + "| TimestepsSoFar | 3.83e+05 |\n", + "| TimeElapsed | 2.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 7.87e-10 |\n", + "| loss_kl | 0.000562 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 8.03e-11 |\n", + "| loss_kl | 0.000509 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | 0.0164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 0.000249 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00426 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0261 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 8.15e-10 |\n", + "| loss_kl | 0.000401 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000803 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 1.63e-09 |\n", + "| loss_kl | 0.00011 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0474 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 268 |\n", + "| TimestepsSoFar | 3.86e+05 |\n", + "| TimeElapsed | 2.06e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0091 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 2.61e-10 |\n", + "| loss_kl | 0.000815 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0081 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 5.29e-10 |\n", + "| loss_kl | 0.000914 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | 0.00499 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00282 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 7.43e-11 |\n", + "| loss_kl | 0.000474 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000564 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.00185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00526 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 0.000412 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.08e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0048 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 2.82e-10 |\n", + "| loss_kl | 0.000621 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.00774 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 270 |\n", + "| TimestepsSoFar | 3.89e+05 |\n", + "| TimeElapsed | 2.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 3.21e-09 |\n", + "| loss_kl | 0.000351 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00592 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000553 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0732 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 4.51e-10 |\n", + "| loss_kl | 0.000199 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 5.19e-10 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0803 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00456 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 0.000475 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.00153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00014 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 6.3e-05 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0328 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 272 |\n", + "| TimestepsSoFar | 3.92e+05 |\n", + "| TimeElapsed | 2.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.234 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 23.4 |\n", + "| ev_tdlam_before | -0.0164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 274 |\n", + "| TimestepsSoFar | 3.95e+05 |\n", + "| TimeElapsed | 2.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00522 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 0.000563 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.00353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 274 |\n", + "| TimestepsSoFar | 3.95e+05 |\n", + "| TimeElapsed | 2.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00545 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 0.000696 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.00666 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 274 |\n", + "| TimestepsSoFar | 3.95e+05 |\n", + "| TimeElapsed | 2.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00625 |\n", + "| loss_pol_entpen | -0.235 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 0.000743 |\n", + "| loss_ent | 23.5 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 274 |\n", + "| TimestepsSoFar | 3.95e+05 |\n", + "| TimeElapsed | 2.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 0.000379 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 274 |\n", + "| TimestepsSoFar | 3.95e+05 |\n", + "| TimeElapsed | 2.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 2.44e-10 |\n", + "| loss_kl | 0.000363 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | 0.00254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 5.93e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.0341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 7.22e-11 |\n", + "| loss_kl | 0.000257 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.0367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0039 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 7e-10 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | 0.00207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.000368 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.00585 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 1.92e-09 |\n", + "| loss_kl | 0.000438 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -5.38e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 276 |\n", + "| TimestepsSoFar | 3.97e+05 |\n", + "| TimeElapsed | 2.13e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 1.98e-09 |\n", + "| loss_kl | 0.000615 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.00412 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.13e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.0845 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 0.000664 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.00305 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00427 |\n", + "| loss_pol_entpen | -0.236 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 0.00051 |\n", + "| loss_ent | 23.6 |\n", + "| ev_tdlam_before | -0.00292 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 7.36e-10 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | 0.000607 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00714 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 9.57e-11 |\n", + "| loss_kl | 0.000698 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | -0.0673 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 278 |\n", + "| TimestepsSoFar | 4e+05 |\n", + "| TimeElapsed | 2.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00541 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 4.54e-10 |\n", + "| loss_kl | 0.000775 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | -0.0358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 8.12e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | 0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000216 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | -0.111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0047 |\n", + "| loss_pol_entpen | -0.237 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 0.000474 |\n", + "| loss_ent | 23.7 |\n", + "| ev_tdlam_before | -0.00918 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.238 |\n", + "| loss_vf_loss | 9.53e-10 |\n", + "| loss_kl | 0.000433 |\n", + "| loss_ent | 23.8 |\n", + "| ev_tdlam_before | -0.00565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.238 |\n", + "| loss_vf_loss | 1.09e-09 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 23.8 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 280 |\n", + "| TimestepsSoFar | 4.03e+05 |\n", + "| TimeElapsed | 2.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.238 |\n", + "| loss_vf_loss | 3.07e-10 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 23.8 |\n", + "| ev_tdlam_before | -0.00277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 282 |\n", + "| TimestepsSoFar | 4.06e+05 |\n", + "| TimeElapsed | 2.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00246 |\n", + "| loss_pol_entpen | -0.238 |\n", + "| loss_vf_loss | 8.06e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 23.8 |\n", + "| ev_tdlam_before | -0.00475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 282 |\n", + "| TimestepsSoFar | 4.06e+05 |\n", + "| TimeElapsed | 2.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.239 |\n", + "| loss_vf_loss | 4.42e-10 |\n", + "| loss_kl | 0.000446 |\n", + "| loss_ent | 23.9 |\n", + "| ev_tdlam_before | -0.00647 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 282 |\n", + "| TimestepsSoFar | 4.06e+05 |\n", + "| TimeElapsed | 2.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0061 |\n", + "| loss_pol_entpen | -0.239 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 0.000557 |\n", + "| loss_ent | 23.9 |\n", + "| ev_tdlam_before | -0.0154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 282 |\n", + "| TimestepsSoFar | 4.06e+05 |\n", + "| TimeElapsed | 2.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00332 |\n", + "| loss_pol_entpen | -0.239 |\n", + "| loss_vf_loss | 5.73e-11 |\n", + "| loss_kl | 0.000563 |\n", + "| loss_ent | 23.9 |\n", + "| ev_tdlam_before | 0.0201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 282 |\n", + "| TimestepsSoFar | 4.06e+05 |\n", + "| TimeElapsed | 2.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.238 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 0.000195 |\n", + "| loss_ent | 23.8 |\n", + "| ev_tdlam_before | 0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00321 |\n", + "| loss_pol_entpen | -0.239 |\n", + "| loss_vf_loss | 9.7e-10 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 23.9 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0108 |\n", + "| loss_pol_entpen | -0.239 |\n", + "| loss_vf_loss | 1.66e-09 |\n", + "| loss_kl | 0.00138 |\n", + "| loss_ent | 23.9 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.18e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.24 |\n", + "| loss_vf_loss | 7.66e-10 |\n", + "| loss_kl | 0.00052 |\n", + "| loss_ent | 24 |\n", + "| ev_tdlam_before | -0.433 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00631 |\n", + "| loss_pol_entpen | -0.24 |\n", + "| loss_vf_loss | 2.6e-10 |\n", + "| loss_kl | 0.000704 |\n", + "| loss_ent | 24 |\n", + "| ev_tdlam_before | -0.0468 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.24 |\n", + "| loss_vf_loss | 2.84e-10 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 24 |\n", + "| ev_tdlam_before | -0.0042 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 284 |\n", + "| TimestepsSoFar | 4.09e+05 |\n", + "| TimeElapsed | 2.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 7.6e-10 |\n", + "| loss_kl | 0.000324 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 2.4e-10 |\n", + "| loss_kl | 0.00032 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.0286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00782 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 6.75e-11 |\n", + "| loss_kl | 0.000594 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 6.12e-10 |\n", + "| loss_kl | 0.00061 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | 0.00331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00335 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 2.08e-09 |\n", + "| loss_kl | 0.000378 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.0237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.2e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000807 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 3.81e-10 |\n", + "| loss_kl | 6.86e-05 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.0932 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 286 |\n", + "| TimestepsSoFar | 4.12e+05 |\n", + "| TimeElapsed | 2.2e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00386 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | 0.00372 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 7.6e-10 |\n", + "| loss_kl | 0.000238 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | 7.8e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.21e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 9.52e-10 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.0434 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.21e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00468 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 4.17e-10 |\n", + "| loss_kl | 0.000371 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.0298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 1.28e-09 |\n", + "| loss_kl | 0.000421 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | 6.51e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.22e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000137 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 4.23e-09 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 288 |\n", + "| TimestepsSoFar | 4.15e+05 |\n", + "| TimeElapsed | 2.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00224 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 0.000248 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.00836 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 290 |\n", + "| TimestepsSoFar | 4.18e+05 |\n", + "| TimeElapsed | 2.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.243 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 24.3 |\n", + "| ev_tdlam_before | -0.00349 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 290 |\n", + "| TimestepsSoFar | 4.18e+05 |\n", + "| TimeElapsed | 2.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00324 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 4.08e-10 |\n", + "| loss_kl | 0.000289 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 290 |\n", + "| TimestepsSoFar | 4.18e+05 |\n", + "| TimeElapsed | 2.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00619 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 5.91e-10 |\n", + "| loss_kl | 0.000615 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 290 |\n", + "| TimestepsSoFar | 4.18e+05 |\n", + "| TimeElapsed | 2.23e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00593 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 2.45e-09 |\n", + "| loss_kl | 0.000769 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.00735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000273 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 290 |\n", + "| TimestepsSoFar | 4.18e+05 |\n", + "| TimeElapsed | 2.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 3.45e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.0192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00575 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 0.000544 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.00173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 1.36e-09 |\n", + "| loss_kl | 0.000267 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | 0.000958 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 7.14e-11 |\n", + "| loss_kl | 0.000268 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | -0.16 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00247 |\n", + "| loss_pol_entpen | -0.241 |\n", + "| loss_vf_loss | 7.73e-10 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 24.1 |\n", + "| ev_tdlam_before | 0.000615 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.001 |\n", + "| loss_pol_entpen | -0.242 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 24.2 |\n", + "| ev_tdlam_before | -0.00501 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 292 |\n", + "| TimestepsSoFar | 4.2e+05 |\n", + "| TimeElapsed | 2.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00755 |\n", + "| loss_pol_entpen | -0.243 |\n", + "| loss_vf_loss | 7.17e-10 |\n", + "| loss_kl | 0.000757 |\n", + "| loss_ent | 24.3 |\n", + "| ev_tdlam_before | -0.0333 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.243 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000623 |\n", + "| loss_ent | 24.3 |\n", + "| ev_tdlam_before | -0.0488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.243 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000417 |\n", + "| loss_ent | 24.3 |\n", + "| ev_tdlam_before | -0.00516 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0102 |\n", + "| loss_pol_entpen | -0.243 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 0.000934 |\n", + "| loss_ent | 24.3 |\n", + "| ev_tdlam_before | -0.0085 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00368 |\n", + "| loss_pol_entpen | -0.244 |\n", + "| loss_vf_loss | 9.65e-10 |\n", + "| loss_kl | 0.000562 |\n", + "| loss_ent | 24.4 |\n", + "| ev_tdlam_before | 0.00138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00393 |\n", + "| loss_pol_entpen | -0.244 |\n", + "| loss_vf_loss | 4.76e-10 |\n", + "| loss_kl | 0.000535 |\n", + "| loss_ent | 24.4 |\n", + "| ev_tdlam_before | -0.0982 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 294 |\n", + "| TimestepsSoFar | 4.23e+05 |\n", + "| TimeElapsed | 2.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.245 |\n", + "| loss_vf_loss | 5.29e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 24.5 |\n", + "| ev_tdlam_before | -0.00823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.245 |\n", + "| loss_vf_loss | 1.37e-09 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 24.5 |\n", + "| ev_tdlam_before | -0.00394 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00731 |\n", + "| loss_pol_entpen | -0.244 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000673 |\n", + "| loss_ent | 24.4 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00452 |\n", + "| loss_pol_entpen | -0.245 |\n", + "| loss_vf_loss | 7.92e-11 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 24.5 |\n", + "| ev_tdlam_before | -0.0271 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00806 |\n", + "| loss_pol_entpen | -0.245 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000823 |\n", + "| loss_ent | 24.5 |\n", + "| ev_tdlam_before | -0.0015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00157 |\n", + "| loss_pol_entpen | -0.245 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.000511 |\n", + "| loss_ent | 24.5 |\n", + "| ev_tdlam_before | -0.00523 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000285 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 296 |\n", + "| TimestepsSoFar | 4.26e+05 |\n", + "| TimeElapsed | 2.28e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00545 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 9.39e-11 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000286 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 298 |\n", + "| TimestepsSoFar | 4.29e+05 |\n", + "| TimeElapsed | 2.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00294 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 5.28e-11 |\n", + "| loss_kl | 0.000464 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.00625 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000286 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 298 |\n", + "| TimestepsSoFar | 4.29e+05 |\n", + "| TimeElapsed | 2.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00316 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 0.000328 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.00303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000286 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 298 |\n", + "| TimestepsSoFar | 4.29e+05 |\n", + "| TimeElapsed | 2.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 0.000191 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.00844 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000286 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 298 |\n", + "| TimestepsSoFar | 4.29e+05 |\n", + "| TimeElapsed | 2.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00353 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 6.1e-10 |\n", + "| loss_kl | 0.000331 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.00738 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000286 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 298 |\n", + "| TimestepsSoFar | 4.29e+05 |\n", + "| TimeElapsed | 2.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 4.52e-10 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.00746 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 4.45e-10 |\n", + "| loss_kl | 0.000266 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.00346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 6.05e-10 |\n", + "| loss_kl | 0.000305 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00594 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000575 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00474 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 0.000577 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00494 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 0.000442 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.00655 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 300 |\n", + "| TimestepsSoFar | 4.32e+05 |\n", + "| TimeElapsed | 2.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000684 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.0726 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.59e-09 |\n", + "| loss_kl | 0.000246 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.0332 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 6.65e-05 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 4.19e-10 |\n", + "| loss_kl | 4.77e-05 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00412 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 2.63e-10 |\n", + "| loss_kl | 0.000329 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.0427 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000869 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 2.84e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00465 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 3.86e-10 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.00375 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 302 |\n", + "| TimestepsSoFar | 4.35e+05 |\n", + "| TimeElapsed | 2.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0023 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 7.67e-10 |\n", + "| loss_kl | 0.000279 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.0743 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00763 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 2.92e-10 |\n", + "| loss_kl | 0.000591 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.000826 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.33e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.37e-09 |\n", + "| loss_kl | 0.000856 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.94e-09 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | 0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 0.00012 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.0482 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00546 |\n", + "| loss_pol_entpen | -0.247 |\n", + "| loss_vf_loss | 1.73e-09 |\n", + "| loss_kl | 0.000568 |\n", + "| loss_ent | 24.7 |\n", + "| ev_tdlam_before | -0.00494 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 304 |\n", + "| TimestepsSoFar | 4.38e+05 |\n", + "| TimeElapsed | 2.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000189 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 3.61e-05 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 306 |\n", + "| TimestepsSoFar | 4.41e+05 |\n", + "| TimeElapsed | 2.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 9.04e-10 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | 0.00825 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 306 |\n", + "| TimestepsSoFar | 4.41e+05 |\n", + "| TimeElapsed | 2.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00471 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 3.77e-10 |\n", + "| loss_kl | 0.000546 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00941 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 306 |\n", + "| TimestepsSoFar | 4.41e+05 |\n", + "| TimeElapsed | 2.35e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000299 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 6.48e-11 |\n", + "| loss_kl | 6.13e-05 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.0396 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 306 |\n", + "| TimestepsSoFar | 4.41e+05 |\n", + "| TimeElapsed | 2.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00964 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000718 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000297 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 306 |\n", + "| TimestepsSoFar | 4.41e+05 |\n", + "| TimeElapsed | 2.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00546 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000494 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 8.27e-10 |\n", + "| loss_kl | 0.000566 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -8.18e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 0.000375 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.0473 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 1.9e-10 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00403 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 4.5e-10 |\n", + "| loss_kl | 0.000391 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00372 |\n", + "| loss_pol_entpen | -0.248 |\n", + "| loss_vf_loss | 3e-10 |\n", + "| loss_kl | 0.000488 |\n", + "| loss_ent | 24.8 |\n", + "| ev_tdlam_before | -0.00858 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 308 |\n", + "| TimestepsSoFar | 4.44e+05 |\n", + "| TimeElapsed | 2.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000282 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | 0.00673 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 0.000351 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | 0.0013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00418 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 0.000355 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | -0.0791 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00477 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 1.23e-09 |\n", + "| loss_kl | 0.000628 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.38e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 2.04e-09 |\n", + "| loss_kl | 0.000354 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | -0.0679 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00226 |\n", + "| loss_pol_entpen | -0.251 |\n", + "| loss_vf_loss | 1.84e-09 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 25.1 |\n", + "| ev_tdlam_before | -0.164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 310 |\n", + "| TimestepsSoFar | 4.46e+05 |\n", + "| TimeElapsed | 2.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00535 |\n", + "| loss_pol_entpen | -0.252 |\n", + "| loss_vf_loss | 7.2e-10 |\n", + "| loss_kl | 0.000572 |\n", + "| loss_ent | 25.2 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.252 |\n", + "| loss_vf_loss | 1.57e-09 |\n", + "| loss_kl | 0.000339 |\n", + "| loss_ent | 25.2 |\n", + "| ev_tdlam_before | -0.0353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.252 |\n", + "| loss_vf_loss | 7.75e-10 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 25.2 |\n", + "| ev_tdlam_before | -0.0627 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00414 |\n", + "| loss_pol_entpen | -0.252 |\n", + "| loss_vf_loss | 3.73e-10 |\n", + "| loss_kl | 0.000355 |\n", + "| loss_ent | 25.2 |\n", + "| ev_tdlam_before | -0.00894 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.252 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 0.000302 |\n", + "| loss_ent | 25.2 |\n", + "| ev_tdlam_before | 0.00179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.253 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 25.3 |\n", + "| ev_tdlam_before | 0.003 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000302 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 312 |\n", + "| TimestepsSoFar | 4.49e+05 |\n", + "| TimeElapsed | 2.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00948 |\n", + "| loss_pol_entpen | -0.254 |\n", + "| loss_vf_loss | 1.35e-09 |\n", + "| loss_kl | 0.000697 |\n", + "| loss_ent | 25.4 |\n", + "| ev_tdlam_before | -0.00222 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 314 |\n", + "| TimestepsSoFar | 4.52e+05 |\n", + "| TimeElapsed | 2.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.254 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000515 |\n", + "| loss_ent | 25.4 |\n", + "| ev_tdlam_before | -0.401 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 314 |\n", + "| TimestepsSoFar | 4.52e+05 |\n", + "| TimeElapsed | 2.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.254 |\n", + "| loss_vf_loss | 5.39e-11 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 25.4 |\n", + "| ev_tdlam_before | -0.0269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 314 |\n", + "| TimestepsSoFar | 4.52e+05 |\n", + "| TimeElapsed | 2.41e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00799 |\n", + "| loss_pol_entpen | -0.254 |\n", + "| loss_vf_loss | 6.64e-11 |\n", + "| loss_kl | 0.000723 |\n", + "| loss_ent | 25.4 |\n", + "| ev_tdlam_before | -0.000243 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 314 |\n", + "| TimestepsSoFar | 4.52e+05 |\n", + "| TimeElapsed | 2.41e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 9.29e-10 |\n", + "| loss_kl | 0.000301 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.000953 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 314 |\n", + "| TimestepsSoFar | 4.52e+05 |\n", + "| TimeElapsed | 2.41e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.002 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0329 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00739 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 6.36e-11 |\n", + "| loss_kl | 0.000662 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.00239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 6.9e-11 |\n", + "| loss_kl | 0.000449 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.00193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 7.69e-11 |\n", + "| loss_kl | 0.00036 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.00748 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00484 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 0.000554 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | 0.00287 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 2.32e-10 |\n", + "| loss_kl | 0.000213 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.00455 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000304 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 316 |\n", + "| TimestepsSoFar | 4.55e+05 |\n", + "| TimeElapsed | 2.43e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0076 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 3.86e-10 |\n", + "| loss_kl | 0.00059 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.00331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.00552 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00583 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 8.48e-10 |\n", + "| loss_kl | 0.000556 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 6.5e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00665 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 4.02e-10 |\n", + "| loss_kl | 0.000738 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.0269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 0.000259 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.041 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 318 |\n", + "| TimestepsSoFar | 4.58e+05 |\n", + "| TimeElapsed | 2.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0876 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0039 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 8.05e-10 |\n", + "| loss_kl | 0.000474 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.257 |\n", + "| loss_vf_loss | 5.46e-10 |\n", + "| loss_kl | 0.000365 |\n", + "| loss_ent | 25.7 |\n", + "| ev_tdlam_before | -0.117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000343 |\n", + "| loss_pol_entpen | -0.257 |\n", + "| loss_vf_loss | 1.83e-10 |\n", + "| loss_kl | 7.15e-05 |\n", + "| loss_ent | 25.7 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00679 |\n", + "| loss_pol_entpen | -0.257 |\n", + "| loss_vf_loss | 4.76e-11 |\n", + "| loss_kl | 0.000503 |\n", + "| loss_ent | 25.7 |\n", + "| ev_tdlam_before | 0.00187 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 9.88e-11 |\n", + "| loss_kl | 0.000321 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.000368 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 320 |\n", + "| TimestepsSoFar | 4.61e+05 |\n", + "| TimeElapsed | 2.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00027 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 7.33e-10 |\n", + "| loss_kl | 9.71e-05 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 322 |\n", + "| TimestepsSoFar | 4.64e+05 |\n", + "| TimeElapsed | 2.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 8.2e-10 |\n", + "| loss_kl | 0.000148 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.00056 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 322 |\n", + "| TimestepsSoFar | 4.64e+05 |\n", + "| TimeElapsed | 2.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0052 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.000315 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 322 |\n", + "| TimestepsSoFar | 4.64e+05 |\n", + "| TimeElapsed | 2.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00668 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 1.19e-09 |\n", + "| loss_kl | 0.00083 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 322 |\n", + "| TimestepsSoFar | 4.64e+05 |\n", + "| TimeElapsed | 2.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00705 |\n", + "| loss_pol_entpen | -0.255 |\n", + "| loss_vf_loss | 2.63e-10 |\n", + "| loss_kl | 0.000834 |\n", + "| loss_ent | 25.5 |\n", + "| ev_tdlam_before | -0.021 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 322 |\n", + "| TimestepsSoFar | 4.64e+05 |\n", + "| TimeElapsed | 2.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 9.64e-10 |\n", + "| loss_kl | 0.00032 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.00834 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00058 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 4.61e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0289 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 3.58e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000776 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.00684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00481 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 5.08e-10 |\n", + "| loss_kl | 0.00046 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 2.31e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00799 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 1.49e-09 |\n", + "| loss_kl | 0.000854 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | 0.00279 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 324 |\n", + "| TimestepsSoFar | 4.67e+05 |\n", + "| TimeElapsed | 2.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00535 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 5.1e-10 |\n", + "| loss_kl | 0.000537 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.00718 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.5e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000741 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 6.17e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.5e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00669 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 0.000543 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0406 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00942 |\n", + "| loss_pol_entpen | -0.256 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 0.00122 |\n", + "| loss_ent | 25.6 |\n", + "| ev_tdlam_before | -0.0081 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00461 |\n", + "| loss_pol_entpen | -0.257 |\n", + "| loss_vf_loss | 8.35e-11 |\n", + "| loss_kl | 0.000666 |\n", + "| loss_ent | 25.7 |\n", + "| ev_tdlam_before | 0.0087 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00491 |\n", + "| loss_pol_entpen | -0.257 |\n", + "| loss_vf_loss | 2.46e-10 |\n", + "| loss_kl | 0.00058 |\n", + "| loss_ent | 25.7 |\n", + "| ev_tdlam_before | 0.000834 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 326 |\n", + "| TimestepsSoFar | 4.69e+05 |\n", + "| TimeElapsed | 2.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | -0.101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00716 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.000779 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | -0.0033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.97e-05 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000128 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | -0.0112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00468 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | -0.00564 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00197 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 4.57e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | -0.01 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 2.74e-09 |\n", + "| loss_kl | 0.000286 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | -0.0287 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 328 |\n", + "| TimestepsSoFar | 4.72e+05 |\n", + "| TimeElapsed | 2.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00548 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 0.000499 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | 0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0003 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 330 |\n", + "| TimestepsSoFar | 4.75e+05 |\n", + "| TimeElapsed | 2.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00595 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 1.23e-09 |\n", + "| loss_kl | 0.000682 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | -0.00509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0003 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 330 |\n", + "| TimestepsSoFar | 4.75e+05 |\n", + "| TimeElapsed | 2.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00306 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 5.54e-11 |\n", + "| loss_kl | 0.000432 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | -0.0799 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0003 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 330 |\n", + "| TimestepsSoFar | 4.75e+05 |\n", + "| TimeElapsed | 2.53e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00549 |\n", + "| loss_pol_entpen | -0.258 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.000574 |\n", + "| loss_ent | 25.8 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0003 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 330 |\n", + "| TimestepsSoFar | 4.75e+05 |\n", + "| TimeElapsed | 2.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00595 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 3.54e-10 |\n", + "| loss_kl | 0.000756 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | -0.0482 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0003 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 330 |\n", + "| TimestepsSoFar | 4.75e+05 |\n", + "| TimeElapsed | 2.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0057 |\n", + "| loss_pol_entpen | -0.259 |\n", + "| loss_vf_loss | 4.41e-10 |\n", + "| loss_kl | 0.000749 |\n", + "| loss_ent | 25.9 |\n", + "| ev_tdlam_before | 0.003 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00918 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 3.03e-09 |\n", + "| loss_kl | 0.00095 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | 0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00655 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 7.14e-10 |\n", + "| loss_kl | 0.000832 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.067 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 6.51e-10 |\n", + "| loss_kl | 0.000249 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.00813 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00606 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000598 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.0339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00467 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 7.83e-10 |\n", + "| loss_kl | 0.000455 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | 0.00222 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000308 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 332 |\n", + "| TimestepsSoFar | 4.78e+05 |\n", + "| TimeElapsed | 2.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 3e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | 0.00261 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 4.98e-10 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.00831 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00403 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 4.13e-09 |\n", + "| loss_kl | 0.000364 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | 0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000373 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.21 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 2.46e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.0069 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00365 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 1.59e-09 |\n", + "| loss_kl | 0.000236 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | 0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000319 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 334 |\n", + "| TimestepsSoFar | 4.81e+05 |\n", + "| TimeElapsed | 2.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0039 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.00041 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.00151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00393 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 9.75e-10 |\n", + "| loss_kl | 0.000542 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.00231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00513 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000454 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0067 |\n", + "| loss_pol_entpen | -0.26 |\n", + "| loss_vf_loss | 2.92e-10 |\n", + "| loss_kl | 0.000761 |\n", + "| loss_ent | 26 |\n", + "| ev_tdlam_before | -0.00278 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000739 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.000254 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | 0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00616 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 0.000489 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | -0.0279 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000315 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 336 |\n", + "| TimestepsSoFar | 4.84e+05 |\n", + "| TimeElapsed | 2.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.262 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 26.2 |\n", + "| ev_tdlam_before | -0.121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000317 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 338 |\n", + "| TimestepsSoFar | 4.87e+05 |\n", + "| TimeElapsed | 2.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00381 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | 0.00306 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000317 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 338 |\n", + "| TimestepsSoFar | 4.87e+05 |\n", + "| TimeElapsed | 2.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00406 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000497 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | -8.5e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000317 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 338 |\n", + "| TimestepsSoFar | 4.87e+05 |\n", + "| TimeElapsed | 2.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 4.24e-10 |\n", + "| loss_kl | 0.000246 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | 0.00189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000317 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 338 |\n", + "| TimestepsSoFar | 4.87e+05 |\n", + "| TimeElapsed | 2.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.261 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 0.000232 |\n", + "| loss_ent | 26.1 |\n", + "| ev_tdlam_before | -0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000317 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 338 |\n", + "| TimestepsSoFar | 4.87e+05 |\n", + "| TimeElapsed | 2.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.262 |\n", + "| loss_vf_loss | 3.13e-10 |\n", + "| loss_kl | 0.000357 |\n", + "| loss_ent | 26.2 |\n", + "| ev_tdlam_before | -0.00468 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.004 |\n", + "| loss_pol_entpen | -0.262 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000372 |\n", + "| loss_ent | 26.2 |\n", + "| ev_tdlam_before | -0.0325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0032 |\n", + "| loss_pol_entpen | -0.262 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 26.2 |\n", + "| ev_tdlam_before | -0.0576 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0129 |\n", + "| loss_pol_entpen | -0.263 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.00146 |\n", + "| loss_ent | 26.3 |\n", + "| ev_tdlam_before | -0.00972 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.263 |\n", + "| loss_vf_loss | 1.48e-09 |\n", + "| loss_kl | 0.000749 |\n", + "| loss_ent | 26.3 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00458 |\n", + "| loss_pol_entpen | -0.263 |\n", + "| loss_vf_loss | 3.36e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 26.3 |\n", + "| ev_tdlam_before | -0.209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 340 |\n", + "| TimestepsSoFar | 4.9e+05 |\n", + "| TimeElapsed | 2.61e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.264 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 26.4 |\n", + "| ev_tdlam_before | -0.000153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.264 |\n", + "| loss_vf_loss | 2.26e-09 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 26.4 |\n", + "| ev_tdlam_before | 0.00529 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.264 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 26.4 |\n", + "| ev_tdlam_before | -0.00881 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.63e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000828 |\n", + "| loss_pol_entpen | -0.264 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 26.4 |\n", + "| ev_tdlam_before | -0.0293 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.63e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.264 |\n", + "| loss_vf_loss | 5.59e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 26.4 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.265 |\n", + "| loss_vf_loss | 4e-09 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 26.5 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000312 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 342 |\n", + "| TimestepsSoFar | 4.92e+05 |\n", + "| TimeElapsed | 2.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.0458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 8.96e-11 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | 0.00355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00467 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 2.97e-10 |\n", + "| loss_kl | 0.000372 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.00301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00748 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 8.31e-10 |\n", + "| loss_kl | 0.000854 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.00503 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00429 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 0.000628 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.0939 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0064 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 0.000538 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.0579 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 344 |\n", + "| TimestepsSoFar | 4.95e+05 |\n", + "| TimeElapsed | 2.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000469 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 4.77e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | 0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 346 |\n", + "| TimestepsSoFar | 4.98e+05 |\n", + "| TimeElapsed | 2.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0027 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 3.48e-09 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | 0.000148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 346 |\n", + "| TimestepsSoFar | 4.98e+05 |\n", + "| TimeElapsed | 2.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.0666 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 346 |\n", + "| TimestepsSoFar | 4.98e+05 |\n", + "| TimeElapsed | 2.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 1.32e-09 |\n", + "| loss_kl | 0.000199 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | 0.00795 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 346 |\n", + "| TimestepsSoFar | 4.98e+05 |\n", + "| TimeElapsed | 2.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 0.00028 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.0163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 346 |\n", + "| TimestepsSoFar | 4.98e+05 |\n", + "| TimeElapsed | 2.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 4.11e-09 |\n", + "| loss_kl | 0.000369 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00647 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 8.87e-11 |\n", + "| loss_kl | 0.000744 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.0737 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0035 |\n", + "| loss_pol_entpen | -0.266 |\n", + "| loss_vf_loss | 7.09e-11 |\n", + "| loss_kl | 0.000557 |\n", + "| loss_ent | 26.6 |\n", + "| ev_tdlam_before | -0.116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 3.8e-10 |\n", + "| loss_kl | 0.000225 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.0326 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.67e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 8.17e-05 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.000239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.67e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 5.8e-09 |\n", + "| loss_kl | 0.000111 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | 0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 348 |\n", + "| TimestepsSoFar | 5.01e+05 |\n", + "| TimeElapsed | 2.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0044 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 1.4e-09 |\n", + "| loss_kl | 0.000268 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00336 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | 0.0258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.267 |\n", + "| loss_vf_loss | 9.97e-11 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 26.7 |\n", + "| ev_tdlam_before | -0.0457 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.69e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00389 |\n", + "| loss_pol_entpen | -0.268 |\n", + "| loss_vf_loss | 7.84e-11 |\n", + "| loss_kl | 0.000441 |\n", + "| loss_ent | 26.8 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00321 |\n", + "| loss_pol_entpen | -0.268 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 0.000374 |\n", + "| loss_ent | 26.8 |\n", + "| ev_tdlam_before | 0.00233 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.268 |\n", + "| loss_vf_loss | 3.82e-10 |\n", + "| loss_kl | 0.000425 |\n", + "| loss_ent | 26.8 |\n", + "| ev_tdlam_before | -0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 350 |\n", + "| TimestepsSoFar | 5.04e+05 |\n", + "| TimeElapsed | 2.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00274 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.52e-09 |\n", + "| loss_kl | 0.000288 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00242 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 2.71e-09 |\n", + "| loss_kl | 0.000305 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.0036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00412 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.55e-09 |\n", + "| loss_kl | 0.000417 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.00966 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000282 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00419 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 0.000496 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.0524 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00366 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 2.54e-10 |\n", + "| loss_kl | 0.000259 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | 0.00164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 352 |\n", + "| TimestepsSoFar | 5.07e+05 |\n", + "| TimeElapsed | 2.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00796 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 0.00081 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.072 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 354 |\n", + "| TimestepsSoFar | 5.1e+05 |\n", + "| TimeElapsed | 2.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0051 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 0.000726 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.055 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 354 |\n", + "| TimestepsSoFar | 5.1e+05 |\n", + "| TimeElapsed | 2.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 5.18e-10 |\n", + "| loss_kl | 0.000482 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.025 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 354 |\n", + "| TimestepsSoFar | 5.1e+05 |\n", + "| TimeElapsed | 2.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 7.12e-10 |\n", + "| loss_kl | 0.000326 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.0581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 354 |\n", + "| TimestepsSoFar | 5.1e+05 |\n", + "| TimeElapsed | 2.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00303 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 2.49e-11 |\n", + "| loss_kl | 0.000334 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.0355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 354 |\n", + "| TimestepsSoFar | 5.1e+05 |\n", + "| TimeElapsed | 2.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000191 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | 0.000424 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00267 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 9e-10 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.00219 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 9.14e-05 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.0358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00775 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.000645 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.00943 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 9.71e-11 |\n", + "| loss_kl | 0.000451 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | -0.054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.73e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00529 |\n", + "| loss_pol_entpen | -0.269 |\n", + "| loss_vf_loss | 3.46e-10 |\n", + "| loss_kl | 0.00055 |\n", + "| loss_ent | 26.9 |\n", + "| ev_tdlam_before | 0.00975 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 356 |\n", + "| TimestepsSoFar | 5.13e+05 |\n", + "| TimeElapsed | 2.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00501 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 0.000519 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00677 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 5.72e-10 |\n", + "| loss_kl | 0.000771 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | -0.115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.27 |\n", + "| loss_vf_loss | 2.97e-09 |\n", + "| loss_kl | 0.000464 |\n", + "| loss_ent | 27 |\n", + "| ev_tdlam_before | 0.00596 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00887 |\n", + "| loss_pol_entpen | -0.271 |\n", + "| loss_vf_loss | 6.11e-09 |\n", + "| loss_kl | 0.000813 |\n", + "| loss_ent | 27.1 |\n", + "| ev_tdlam_before | -0.37 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.271 |\n", + "| loss_vf_loss | 1.92e-09 |\n", + "| loss_kl | 0.000408 |\n", + "| loss_ent | 27.1 |\n", + "| ev_tdlam_before | -0.712 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00339 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 4.65e-11 |\n", + "| loss_kl | 0.000366 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0357 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 358 |\n", + "| TimestepsSoFar | 5.16e+05 |\n", + "| TimeElapsed | 2.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00773 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.84e-09 |\n", + "| loss_kl | 0.000836 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0469 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00398 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 4.29e-10 |\n", + "| loss_kl | 0.000604 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.24e-11 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | 0.0204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000386 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 5.54e-05 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -6.91e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.76e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0071 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.09e-09 |\n", + "| loss_kl | 0.000145 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0873 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 360 |\n", + "| TimestepsSoFar | 5.18e+05 |\n", + "| TimeElapsed | 2.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00337 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 4.54e-10 |\n", + "| loss_kl | 0.000325 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 362 |\n", + "| TimestepsSoFar | 5.21e+05 |\n", + "| TimeElapsed | 2.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 4.12e-10 |\n", + "| loss_kl | 0.00011 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0464 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 362 |\n", + "| TimestepsSoFar | 5.21e+05 |\n", + "| TimeElapsed | 2.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 2.87e-09 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 362 |\n", + "| TimestepsSoFar | 5.21e+05 |\n", + "| TimeElapsed | 2.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00576 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 6.83e-09 |\n", + "| loss_kl | 0.000621 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.0893 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 362 |\n", + "| TimestepsSoFar | 5.21e+05 |\n", + "| TimeElapsed | 2.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00279 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.17e-10 |\n", + "| loss_kl | 0.00041 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -1.09 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000281 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 362 |\n", + "| TimestepsSoFar | 5.21e+05 |\n", + "| TimeElapsed | 2.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.15e-10 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.00053 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.79e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000268 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -5.96e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 7.64e-11 |\n", + "| loss_kl | 0.000438 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.00773 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00539 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000516 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.00661 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00184 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 5.11e-11 |\n", + "| loss_kl | 0.000327 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000976 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 8.3e-05 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | 0.000371 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 364 |\n", + "| TimestepsSoFar | 5.24e+05 |\n", + "| TimeElapsed | 2.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00403 |\n", + "| loss_pol_entpen | -0.272 |\n", + "| loss_vf_loss | 3.3e-10 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 27.2 |\n", + "| ev_tdlam_before | -0.00868 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000952 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 2.02e-09 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | 0.00553 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00471 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 1.2e-09 |\n", + "| loss_kl | 0.000398 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.0373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 8.77e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00904 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 3.11e-10 |\n", + "| loss_kl | 0.000818 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.0206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00463 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 2.51e-09 |\n", + "| loss_kl | 0.000569 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.00362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 366 |\n", + "| TimestepsSoFar | 5.27e+05 |\n", + "| TimeElapsed | 2.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000222 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | 0.00211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.273 |\n", + "| loss_vf_loss | 1.94e-09 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 27.3 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00407 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 1.32e-09 |\n", + "| loss_kl | 0.000372 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.0779 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 2.29e-09 |\n", + "| loss_kl | 0.000318 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 9.61e-10 |\n", + "| loss_kl | 0.000248 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.11 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 4.94e-11 |\n", + "| loss_kl | 0.00031 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.089 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 368 |\n", + "| TimestepsSoFar | 5.3e+05 |\n", + "| TimeElapsed | 2.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00324 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 4.6e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0785 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 370 |\n", + "| TimestepsSoFar | 5.33e+05 |\n", + "| TimeElapsed | 2.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00359 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 9.44e-11 |\n", + "| loss_kl | 0.000392 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0399 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 370 |\n", + "| TimestepsSoFar | 5.33e+05 |\n", + "| TimeElapsed | 2.84e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00387 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 0.000392 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.00802 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 370 |\n", + "| TimestepsSoFar | 5.33e+05 |\n", + "| TimeElapsed | 2.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00447 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 5.94e-10 |\n", + "| loss_kl | 0.000421 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 370 |\n", + "| TimestepsSoFar | 5.33e+05 |\n", + "| TimeElapsed | 2.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000306 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0415 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 370 |\n", + "| TimestepsSoFar | 5.33e+05 |\n", + "| TimeElapsed | 2.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 9.01e-11 |\n", + "| loss_kl | 0.000227 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00368 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 4.95e-09 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.000639 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000585 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 5.09e-11 |\n", + "| loss_kl | 8.98e-05 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00598 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000478 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00366 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 7.95e-11 |\n", + "| loss_kl | 0.000591 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.00957 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.274 |\n", + "| loss_vf_loss | 1.42e-09 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 27.4 |\n", + "| ev_tdlam_before | -0.0134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 372 |\n", + "| TimestepsSoFar | 5.36e+05 |\n", + "| TimeElapsed | 2.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 3.52e-09 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -2.94e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 8.18e-11 |\n", + "| loss_kl | 0.000147 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.15 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00268 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.00195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00443 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.000414 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.00348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 0.000236 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | 0.00159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00261 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.14e-09 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.00055 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 374 |\n", + "| TimestepsSoFar | 5.39e+05 |\n", + "| TimeElapsed | 2.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00279 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 3.11e-10 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00367 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0065 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 5.13e-10 |\n", + "| loss_kl | 0.000511 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.00768 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00671 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.36e-09 |\n", + "| loss_kl | 0.000785 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.00156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.89e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00407 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.14e-09 |\n", + "| loss_kl | 0.000526 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.077 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0042 |\n", + "| loss_pol_entpen | -0.275 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 0.000506 |\n", + "| loss_ent | 27.5 |\n", + "| ev_tdlam_before | -0.0569 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000276 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 376 |\n", + "| TimestepsSoFar | 5.41e+05 |\n", + "| TimeElapsed | 2.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 4.18e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | 0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 378 |\n", + "| TimestepsSoFar | 5.44e+05 |\n", + "| TimeElapsed | 2.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00605 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 4.84e-10 |\n", + "| loss_kl | 0.00052 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0683 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 378 |\n", + "| TimestepsSoFar | 5.44e+05 |\n", + "| TimeElapsed | 2.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 3.54e-09 |\n", + "| loss_kl | 0.000551 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.072 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 378 |\n", + "| TimestepsSoFar | 5.44e+05 |\n", + "| TimeElapsed | 2.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00041 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 5.65e-10 |\n", + "| loss_kl | 6.62e-05 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.719 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 378 |\n", + "| TimestepsSoFar | 5.44e+05 |\n", + "| TimeElapsed | 2.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00266 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0987 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 378 |\n", + "| TimestepsSoFar | 5.44e+05 |\n", + "| TimeElapsed | 2.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00625 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 9.75e-11 |\n", + "| loss_kl | 0.000823 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00337 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 8.09e-11 |\n", + "| loss_kl | 0.000443 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.00249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 4.18e-09 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.0083 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000306 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.00016 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | 0.00395 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.276 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 0.000216 |\n", + "| loss_ent | 27.6 |\n", + "| ev_tdlam_before | -0.067 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 380 |\n", + "| TimestepsSoFar | 5.47e+05 |\n", + "| TimeElapsed | 2.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00545 |\n", + "| loss_pol_entpen | -0.278 |\n", + "| loss_vf_loss | 2.87e-10 |\n", + "| loss_kl | 0.000688 |\n", + "| loss_ent | 27.8 |\n", + "| ev_tdlam_before | 0.000439 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00226 |\n", + "| loss_pol_entpen | -0.278 |\n", + "| loss_vf_loss | 1.93e-09 |\n", + "| loss_kl | 0.000339 |\n", + "| loss_ent | 27.8 |\n", + "| ev_tdlam_before | -0.00371 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.278 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 27.8 |\n", + "| ev_tdlam_before | -0.141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00597 |\n", + "| loss_pol_entpen | -0.279 |\n", + "| loss_vf_loss | 6.15e-10 |\n", + "| loss_kl | 0.00062 |\n", + "| loss_ent | 27.9 |\n", + "| ev_tdlam_before | -0.00374 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00436 |\n", + "| loss_pol_entpen | -0.279 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 0.000732 |\n", + "| loss_ent | 27.9 |\n", + "| ev_tdlam_before | -0.0314 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.279 |\n", + "| loss_vf_loss | 5.15e-10 |\n", + "| loss_kl | 0.000267 |\n", + "| loss_ent | 27.9 |\n", + "| ev_tdlam_before | -0.017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000279 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 382 |\n", + "| TimestepsSoFar | 5.5e+05 |\n", + "| TimeElapsed | 2.93e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0032 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 2.73e-09 |\n", + "| loss_kl | 0.000424 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.279 |\n", + "| loss_vf_loss | 9.78e-11 |\n", + "| loss_kl | 0.000218 |\n", + "| loss_ent | 27.9 |\n", + "| ev_tdlam_before | -0.205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00452 |\n", + "| loss_pol_entpen | -0.279 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000347 |\n", + "| loss_ent | 27.9 |\n", + "| ev_tdlam_before | -0.00051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00274 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 4.05e-10 |\n", + "| loss_kl | 0.000313 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | 0.00207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 6.58e-05 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.0764 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00456 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 8.38e-10 |\n", + "| loss_kl | 0.000298 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.0211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 384 |\n", + "| TimestepsSoFar | 5.53e+05 |\n", + "| TimeElapsed | 2.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 2.55e-10 |\n", + "| loss_kl | 0.000216 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 386 |\n", + "| TimestepsSoFar | 5.56e+05 |\n", + "| TimeElapsed | 2.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 7.44e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.0235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 386 |\n", + "| TimestepsSoFar | 5.56e+05 |\n", + "| TimeElapsed | 2.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 1.94e-09 |\n", + "| loss_kl | 0.000267 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.099 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 386 |\n", + "| TimestepsSoFar | 5.56e+05 |\n", + "| TimeElapsed | 2.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00856 |\n", + "| loss_pol_entpen | -0.28 |\n", + "| loss_vf_loss | 9.81e-11 |\n", + "| loss_kl | 0.000598 |\n", + "| loss_ent | 28 |\n", + "| ev_tdlam_before | -0.0408 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 386 |\n", + "| TimestepsSoFar | 5.56e+05 |\n", + "| TimeElapsed | 2.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00407 |\n", + "| loss_pol_entpen | -0.281 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 0.000758 |\n", + "| loss_ent | 28.1 |\n", + "| ev_tdlam_before | -0.000201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 386 |\n", + "| TimestepsSoFar | 5.56e+05 |\n", + "| TimeElapsed | 2.96e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -2.71e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.97e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00396 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 2.33e-09 |\n", + "| loss_kl | 0.000409 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 3.9e-09 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.0445 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 4.87e-11 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.413 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00915 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 2.75e-09 |\n", + "| loss_kl | 0.000745 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00602 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 1.11e-09 |\n", + "| loss_kl | 0.000899 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 388 |\n", + "| TimestepsSoFar | 5.59e+05 |\n", + "| TimeElapsed | 2.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00267 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000241 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 2.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.282 |\n", + "| loss_vf_loss | 5.73e-10 |\n", + "| loss_kl | 0.000334 |\n", + "| loss_ent | 28.2 |\n", + "| ev_tdlam_before | -0.00346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 2.99e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.283 |\n", + "| loss_vf_loss | 1.24e-09 |\n", + "| loss_kl | 0.000329 |\n", + "| loss_ent | 28.3 |\n", + "| ev_tdlam_before | -0.0281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 2.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00693 |\n", + "| loss_pol_entpen | -0.283 |\n", + "| loss_vf_loss | 8.79e-11 |\n", + "| loss_kl | 0.000613 |\n", + "| loss_ent | 28.3 |\n", + "| ev_tdlam_before | -0.0937 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 2.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0003 |\n", + "| loss_pol_entpen | -0.283 |\n", + "| loss_vf_loss | 5.18e-10 |\n", + "| loss_kl | 0.000221 |\n", + "| loss_ent | 28.3 |\n", + "| ev_tdlam_before | -0.0756 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 2.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.283 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 0.000166 |\n", + "| loss_ent | 28.3 |\n", + "| ev_tdlam_before | -0.0794 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 390 |\n", + "| TimestepsSoFar | 5.62e+05 |\n", + "| TimeElapsed | 3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 8.92e-10 |\n", + "| loss_kl | 0.000266 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.00827 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 1.86e-09 |\n", + "| loss_kl | 0.00022 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0054 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 6.74e-11 |\n", + "| loss_kl | 0.000582 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3.01e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00415 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 1.9e-09 |\n", + "| loss_kl | 0.000363 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.000564 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00325 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 2.71e-10 |\n", + "| loss_kl | 0.000326 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | 0.00639 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00042 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 8.51e-05 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.0594 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 392 |\n", + "| TimestepsSoFar | 5.64e+05 |\n", + "| TimeElapsed | 3.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00586 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 0.000558 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.0386 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 394 |\n", + "| TimestepsSoFar | 5.67e+05 |\n", + "| TimeElapsed | 3.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00487 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 2.62e-10 |\n", + "| loss_kl | 0.000431 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.0169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 394 |\n", + "| TimestepsSoFar | 5.67e+05 |\n", + "| TimeElapsed | 3.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 2.07e-10 |\n", + "| loss_kl | 0.00026 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.00899 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 394 |\n", + "| TimestepsSoFar | 5.67e+05 |\n", + "| TimeElapsed | 3.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00464 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 4.94e-11 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 394 |\n", + "| TimestepsSoFar | 5.67e+05 |\n", + "| TimeElapsed | 3.02e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00715 |\n", + "| loss_pol_entpen | -0.284 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 0.000741 |\n", + "| loss_ent | 28.4 |\n", + "| ev_tdlam_before | -0.000285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 394 |\n", + "| TimestepsSoFar | 5.67e+05 |\n", + "| TimeElapsed | 3.02e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0102 |\n", + "| loss_pol_entpen | -0.285 |\n", + "| loss_vf_loss | 2.48e-09 |\n", + "| loss_kl | 0.000864 |\n", + "| loss_ent | 28.5 |\n", + "| ev_tdlam_before | -0.22 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.285 |\n", + "| loss_vf_loss | 9.24e-10 |\n", + "| loss_kl | 0.000642 |\n", + "| loss_ent | 28.5 |\n", + "| ev_tdlam_before | -0.311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00269 |\n", + "| loss_pol_entpen | -0.285 |\n", + "| loss_vf_loss | 8.77e-11 |\n", + "| loss_kl | 0.000252 |\n", + "| loss_ent | 28.5 |\n", + "| ev_tdlam_before | -0.0313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.04e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00593 |\n", + "| loss_pol_entpen | -0.286 |\n", + "| loss_vf_loss | 1.73e-09 |\n", + "| loss_kl | 0.000602 |\n", + "| loss_ent | 28.6 |\n", + "| ev_tdlam_before | -0.000878 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.04e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.286 |\n", + "| loss_vf_loss | 7.92e-10 |\n", + "| loss_kl | 0.000578 |\n", + "| loss_ent | 28.6 |\n", + "| ev_tdlam_before | -0.0445 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00445 |\n", + "| loss_pol_entpen | -0.286 |\n", + "| loss_vf_loss | 5.3e-11 |\n", + "| loss_kl | 0.000401 |\n", + "| loss_ent | 28.6 |\n", + "| ev_tdlam_before | 0.00272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 396 |\n", + "| TimestepsSoFar | 5.7e+05 |\n", + "| TimeElapsed | 3.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.286 |\n", + "| loss_vf_loss | 1.41e-09 |\n", + "| loss_kl | 0.000307 |\n", + "| loss_ent | 28.6 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.287 |\n", + "| loss_vf_loss | 2.07e-09 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 28.7 |\n", + "| ev_tdlam_before | -0.0536 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00817 |\n", + "| loss_pol_entpen | -0.287 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.00082 |\n", + "| loss_ent | 28.7 |\n", + "| ev_tdlam_before | -0.124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.53e-05 |\n", + "| loss_pol_entpen | -0.287 |\n", + "| loss_vf_loss | 6.23e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 28.7 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.287 |\n", + "| loss_vf_loss | 9.29e-11 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 28.7 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00142 |\n", + "| loss_pol_entpen | -0.287 |\n", + "| loss_vf_loss | 6.28e-10 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 28.7 |\n", + "| ev_tdlam_before | -0.00175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 398 |\n", + "| TimestepsSoFar | 5.73e+05 |\n", + "| TimeElapsed | 3.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00568 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 1.65e-09 |\n", + "| loss_kl | 0.000585 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.00676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 7.99e-10 |\n", + "| loss_kl | 0.000533 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.00778 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00428 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 3.99e-09 |\n", + "| loss_kl | 0.000468 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.00842 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.07e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000264 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 6.82e-10 |\n", + "| loss_kl | 9.9e-05 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.07e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00279 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 1.83e-10 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.0252 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00282 |\n", + "| loss_pol_entpen | -0.288 |\n", + "| loss_vf_loss | 4.13e-09 |\n", + "| loss_kl | 0.000308 |\n", + "| loss_ent | 28.8 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 400 |\n", + "| TimestepsSoFar | 5.76e+05 |\n", + "| TimeElapsed | 3.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.29 |\n", + "| loss_vf_loss | 6.71e-10 |\n", + "| loss_kl | 0.000308 |\n", + "| loss_ent | 29 |\n", + "| ev_tdlam_before | 0.000476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 402 |\n", + "| TimestepsSoFar | 5.79e+05 |\n", + "| TimeElapsed | 3.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000992 |\n", + "| loss_pol_entpen | -0.29 |\n", + "| loss_vf_loss | 1.22e-09 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 29 |\n", + "| ev_tdlam_before | -0.038 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 402 |\n", + "| TimestepsSoFar | 5.79e+05 |\n", + "| TimeElapsed | 3.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.29 |\n", + "| loss_vf_loss | 6.11e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 29 |\n", + "| ev_tdlam_before | -0.041 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 402 |\n", + "| TimestepsSoFar | 5.79e+05 |\n", + "| TimeElapsed | 3.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.291 |\n", + "| loss_vf_loss | 6.97e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 29.1 |\n", + "| ev_tdlam_before | -0.00513 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 402 |\n", + "| TimestepsSoFar | 5.79e+05 |\n", + "| TimeElapsed | 3.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.291 |\n", + "| loss_vf_loss | 9.17e-11 |\n", + "| loss_kl | 0.000392 |\n", + "| loss_ent | 29.1 |\n", + "| ev_tdlam_before | -0.0367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 402 |\n", + "| TimestepsSoFar | 5.79e+05 |\n", + "| TimeElapsed | 3.09e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00444 |\n", + "| loss_pol_entpen | -0.291 |\n", + "| loss_vf_loss | 3.59e-09 |\n", + "| loss_kl | 0.000462 |\n", + "| loss_ent | 29.1 |\n", + "| ev_tdlam_before | -0.0325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00245 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 1.35e-09 |\n", + "| loss_kl | 0.000432 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | -0.478 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | -0.188 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0047 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 0.00052 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | 0.0242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.293 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.00047 |\n", + "| loss_ent | 29.3 |\n", + "| ev_tdlam_before | -0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.293 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 29.3 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 404 |\n", + "| TimestepsSoFar | 5.82e+05 |\n", + "| TimeElapsed | 3.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00181 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 0.000291 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | -0.00718 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 4.73e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | 0.00368 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 7.17e-05 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | 0.000675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 0.000254 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | 0.00056 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.11e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.292 |\n", + "| loss_vf_loss | 8.95e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 29.2 |\n", + "| ev_tdlam_before | -7.88e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00427 |\n", + "| loss_pol_entpen | -0.293 |\n", + "| loss_vf_loss | 3.91e-10 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 29.3 |\n", + "| ev_tdlam_before | -0.00688 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 406 |\n", + "| TimestepsSoFar | 5.85e+05 |\n", + "| TimeElapsed | 3.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000528 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 1.37e-09 |\n", + "| loss_kl | 5.45e-05 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | 0.0016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00116 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 5.65e-11 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -0.0911 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00636 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 0.000483 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | 0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 7.38e-10 |\n", + "| loss_kl | 0.000482 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | 0.00207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00268 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 2.07e-10 |\n", + "| loss_kl | 0.000369 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -0.0309 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 6.74e-10 |\n", + "| loss_kl | 0.000177 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | 7.37e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 408 |\n", + "| TimestepsSoFar | 5.88e+05 |\n", + "| TimeElapsed | 3.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000298 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 3.68e-10 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | 0.000317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 410 |\n", + "| TimestepsSoFar | 5.9e+05 |\n", + "| TimeElapsed | 3.14e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 3.83e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -0.0398 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 410 |\n", + "| TimestepsSoFar | 5.9e+05 |\n", + "| TimeElapsed | 3.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 410 |\n", + "| TimestepsSoFar | 5.9e+05 |\n", + "| TimeElapsed | 3.14e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000439 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 4.56e-10 |\n", + "| loss_kl | 3.62e-05 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 410 |\n", + "| TimestepsSoFar | 5.9e+05 |\n", + "| TimeElapsed | 3.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.294 |\n", + "| loss_vf_loss | 1.93e-09 |\n", + "| loss_kl | 0.000222 |\n", + "| loss_ent | 29.4 |\n", + "| ev_tdlam_before | -9.81e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 410 |\n", + "| TimestepsSoFar | 5.9e+05 |\n", + "| TimeElapsed | 3.15e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.295 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000155 |\n", + "| loss_ent | 29.5 |\n", + "| ev_tdlam_before | -0.132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.295 |\n", + "| loss_vf_loss | 8.43e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 29.5 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00515 |\n", + "| loss_pol_entpen | -0.295 |\n", + "| loss_vf_loss | 9.16e-10 |\n", + "| loss_kl | 0.000519 |\n", + "| loss_ent | 29.5 |\n", + "| ev_tdlam_before | -0.00046 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000502 |\n", + "| loss_pol_entpen | -0.295 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 0.000209 |\n", + "| loss_ent | 29.5 |\n", + "| ev_tdlam_before | -0.0852 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.296 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 29.6 |\n", + "| ev_tdlam_before | -0.000903 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00245 |\n", + "| loss_pol_entpen | -0.296 |\n", + "| loss_vf_loss | 7.63e-11 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 29.6 |\n", + "| ev_tdlam_before | -0.125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 412 |\n", + "| TimestepsSoFar | 5.93e+05 |\n", + "| TimeElapsed | 3.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00683 |\n", + "| loss_pol_entpen | -0.296 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000606 |\n", + "| loss_ent | 29.6 |\n", + "| ev_tdlam_before | -0.0201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.297 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 29.7 |\n", + "| ev_tdlam_before | -0.00467 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.17e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000198 |\n", + "| loss_pol_entpen | -0.297 |\n", + "| loss_vf_loss | 1.71e-09 |\n", + "| loss_kl | 0.0001 |\n", + "| loss_ent | 29.7 |\n", + "| ev_tdlam_before | -0.000432 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.17e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000883 |\n", + "| loss_pol_entpen | -0.297 |\n", + "| loss_vf_loss | 3.43e-10 |\n", + "| loss_kl | 6.85e-05 |\n", + "| loss_ent | 29.7 |\n", + "| ev_tdlam_before | -0.0884 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.18e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000997 |\n", + "| loss_pol_entpen | -0.297 |\n", + "| loss_vf_loss | 4.52e-11 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 29.7 |\n", + "| ev_tdlam_before | -0.0529 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.18e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000623 |\n", + "| loss_pol_entpen | -0.297 |\n", + "| loss_vf_loss | 3.23e-10 |\n", + "| loss_kl | 6.97e-05 |\n", + "| loss_ent | 29.7 |\n", + "| ev_tdlam_before | -0.00237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 414 |\n", + "| TimestepsSoFar | 5.96e+05 |\n", + "| TimeElapsed | 3.18e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00503 |\n", + "| loss_pol_entpen | -0.298 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 0.000487 |\n", + "| loss_ent | 29.8 |\n", + "| ev_tdlam_before | -0.103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0027 |\n", + "| loss_pol_entpen | -0.298 |\n", + "| loss_vf_loss | 5.08e-10 |\n", + "| loss_kl | 0.000331 |\n", + "| loss_ent | 29.8 |\n", + "| ev_tdlam_before | -0.00952 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.298 |\n", + "| loss_vf_loss | 6.23e-11 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 29.8 |\n", + "| ev_tdlam_before | -0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.299 |\n", + "| loss_vf_loss | 2.98e-09 |\n", + "| loss_kl | 0.000379 |\n", + "| loss_ent | 29.9 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00497 |\n", + "| loss_pol_entpen | -0.299 |\n", + "| loss_vf_loss | 8.2e-09 |\n", + "| loss_kl | 0.000515 |\n", + "| loss_ent | 29.9 |\n", + "| ev_tdlam_before | -0.148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00583 |\n", + "| loss_pol_entpen | -0.299 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 0.000609 |\n", + "| loss_ent | 29.9 |\n", + "| ev_tdlam_before | -1.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 416 |\n", + "| TimestepsSoFar | 5.99e+05 |\n", + "| TimeElapsed | 3.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000386 |\n", + "| loss_pol_entpen | -0.3 |\n", + "| loss_vf_loss | 6.74e-10 |\n", + "| loss_kl | 7.75e-05 |\n", + "| loss_ent | 30 |\n", + "| ev_tdlam_before | -0.0191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 418 |\n", + "| TimestepsSoFar | 6.02e+05 |\n", + "| TimeElapsed | 3.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00423 |\n", + "| loss_pol_entpen | -0.3 |\n", + "| loss_vf_loss | 2.32e-10 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 30 |\n", + "| ev_tdlam_before | -0.057 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 418 |\n", + "| TimestepsSoFar | 6.02e+05 |\n", + "| TimeElapsed | 3.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.3 |\n", + "| loss_vf_loss | 6.85e-10 |\n", + "| loss_kl | 0.000394 |\n", + "| loss_ent | 30 |\n", + "| ev_tdlam_before | -0.0337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 418 |\n", + "| TimestepsSoFar | 6.02e+05 |\n", + "| TimeElapsed | 3.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.3 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 30 |\n", + "| ev_tdlam_before | -0.0734 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 418 |\n", + "| TimestepsSoFar | 6.02e+05 |\n", + "| TimeElapsed | 3.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.3 |\n", + "| loss_vf_loss | 2.98e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 30 |\n", + "| ev_tdlam_before | -0.0675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 418 |\n", + "| TimestepsSoFar | 6.02e+05 |\n", + "| TimeElapsed | 3.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 9.41e-10 |\n", + "| loss_kl | 0.000164 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00584 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 9.66e-11 |\n", + "| loss_kl | 0.000492 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 2.43e-09 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0359 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 1.45e-08 |\n", + "| loss_kl | 0.000159 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0681 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00058 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 4.89e-09 |\n", + "| loss_kl | 7.44e-05 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.493 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00362 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000332 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0656 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 420 |\n", + "| TimestepsSoFar | 6.05e+05 |\n", + "| TimeElapsed | 3.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 5.42e-10 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.00625 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 3.62e-10 |\n", + "| loss_kl | 0.000234 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0536 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -4.52e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.24e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00433 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 0.000382 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | 0.00123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00152 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 2.06e-09 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0677 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.24e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 4.37e-11 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000271 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 422 |\n", + "| TimestepsSoFar | 6.08e+05 |\n", + "| TimeElapsed | 3.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 0.000463 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000346 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 3.18e-09 |\n", + "| loss_kl | 0.000146 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0709 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000242 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 3.78e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.22 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000764 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 6.82e-05 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.006 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00306 |\n", + "| loss_pol_entpen | -0.301 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 30.1 |\n", + "| ev_tdlam_before | -0.0408 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00789 |\n", + "| loss_pol_entpen | -0.302 |\n", + "| loss_vf_loss | 1.49e-09 |\n", + "| loss_kl | 0.000585 |\n", + "| loss_ent | 30.2 |\n", + "| ev_tdlam_before | -0.00081 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 424 |\n", + "| TimestepsSoFar | 6.11e+05 |\n", + "| TimeElapsed | 3.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 0.000436 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.0608 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 426 |\n", + "| TimestepsSoFar | 6.13e+05 |\n", + "| TimeElapsed | 3.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00317 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 3.68e-10 |\n", + "| loss_kl | 0.000315 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | 0.000531 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 426 |\n", + "| TimestepsSoFar | 6.13e+05 |\n", + "| TimeElapsed | 3.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 0.000248 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 426 |\n", + "| TimestepsSoFar | 6.13e+05 |\n", + "| TimeElapsed | 3.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 6.02e-11 |\n", + "| loss_kl | 0.000279 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | 0.00997 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 426 |\n", + "| TimestepsSoFar | 6.13e+05 |\n", + "| TimeElapsed | 3.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00377 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 5.85e-10 |\n", + "| loss_kl | 0.000365 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | 1.39e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 426 |\n", + "| TimestepsSoFar | 6.13e+05 |\n", + "| TimeElapsed | 3.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 2.86e-09 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 2.18e-09 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.38 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 3.27e-10 |\n", + "| loss_kl | 0.000247 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 1.17e-09 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.00393 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000228 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.303 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 30.3 |\n", + "| ev_tdlam_before | -0.00691 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 428 |\n", + "| TimestepsSoFar | 6.16e+05 |\n", + "| TimeElapsed | 3.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00275 |\n", + "| loss_pol_entpen | -0.304 |\n", + "| loss_vf_loss | 1.5e-09 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 30.4 |\n", + "| ev_tdlam_before | -0.0592 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.29e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00304 |\n", + "| loss_pol_entpen | -0.304 |\n", + "| loss_vf_loss | 1.85e-09 |\n", + "| loss_kl | 0.000364 |\n", + "| loss_ent | 30.4 |\n", + "| ev_tdlam_before | -0.0893 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.304 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 30.4 |\n", + "| ev_tdlam_before | -0.0244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.304 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 30.4 |\n", + "| ev_tdlam_before | 0.00764 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.305 |\n", + "| loss_vf_loss | 6.41e-10 |\n", + "| loss_kl | 0.000406 |\n", + "| loss_ent | 30.5 |\n", + "| ev_tdlam_before | -0.0089 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00466 |\n", + "| loss_pol_entpen | -0.305 |\n", + "| loss_vf_loss | 1.86e-09 |\n", + "| loss_kl | 0.000435 |\n", + "| loss_ent | 30.5 |\n", + "| ev_tdlam_before | 0.00379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 430 |\n", + "| TimestepsSoFar | 6.19e+05 |\n", + "| TimeElapsed | 3.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.306 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 0.000371 |\n", + "| loss_ent | 30.6 |\n", + "| ev_tdlam_before | -0.0255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00506 |\n", + "| loss_pol_entpen | -0.306 |\n", + "| loss_vf_loss | 6.97e-10 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 30.6 |\n", + "| ev_tdlam_before | 0.00211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.306 |\n", + "| loss_vf_loss | 1.59e-09 |\n", + "| loss_kl | 0.000348 |\n", + "| loss_ent | 30.6 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000944 |\n", + "| loss_pol_entpen | -0.307 |\n", + "| loss_vf_loss | 2.17e-09 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 30.7 |\n", + "| ev_tdlam_before | -0.115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.31e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00523 |\n", + "| loss_pol_entpen | -0.307 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 0.000442 |\n", + "| loss_ent | 30.7 |\n", + "| ev_tdlam_before | -0.256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.307 |\n", + "| loss_vf_loss | 4.85e-09 |\n", + "| loss_kl | 0.000347 |\n", + "| loss_ent | 30.7 |\n", + "| ev_tdlam_before | -0.0075 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 432 |\n", + "| TimestepsSoFar | 6.22e+05 |\n", + "| TimeElapsed | 3.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00434 |\n", + "| loss_pol_entpen | -0.308 |\n", + "| loss_vf_loss | 4.89e-10 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 30.8 |\n", + "| ev_tdlam_before | -0.000362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 434 |\n", + "| TimestepsSoFar | 6.25e+05 |\n", + "| TimeElapsed | 3.32e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000714 |\n", + "| loss_pol_entpen | -0.308 |\n", + "| loss_vf_loss | 1.91e-09 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 30.8 |\n", + "| ev_tdlam_before | -0.0557 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 434 |\n", + "| TimestepsSoFar | 6.25e+05 |\n", + "| TimeElapsed | 3.33e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00356 |\n", + "| loss_pol_entpen | -0.308 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000326 |\n", + "| loss_ent | 30.8 |\n", + "| ev_tdlam_before | -0.18 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 434 |\n", + "| TimestepsSoFar | 6.25e+05 |\n", + "| TimeElapsed | 3.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00563 |\n", + "| loss_pol_entpen | -0.308 |\n", + "| loss_vf_loss | 1.53e-09 |\n", + "| loss_kl | 0.000516 |\n", + "| loss_ent | 30.8 |\n", + "| ev_tdlam_before | -0.00957 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 434 |\n", + "| TimestepsSoFar | 6.25e+05 |\n", + "| TimeElapsed | 3.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00223 |\n", + "| loss_pol_entpen | -0.308 |\n", + "| loss_vf_loss | 7.12e-11 |\n", + "| loss_kl | 0.000323 |\n", + "| loss_ent | 30.8 |\n", + "| ev_tdlam_before | -0.389 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 434 |\n", + "| TimestepsSoFar | 6.25e+05 |\n", + "| TimeElapsed | 3.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.309 |\n", + "| loss_vf_loss | 9.81e-09 |\n", + "| loss_kl | 0.000316 |\n", + "| loss_ent | 30.9 |\n", + "| ev_tdlam_before | -0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.31 |\n", + "| loss_vf_loss | 6.11e-10 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 31 |\n", + "| ev_tdlam_before | -0.316 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00331 |\n", + "| loss_pol_entpen | -0.31 |\n", + "| loss_vf_loss | 1.68e-08 |\n", + "| loss_kl | 0.000366 |\n", + "| loss_ent | 31 |\n", + "| ev_tdlam_before | -0.000775 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.34e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00301 |\n", + "| loss_pol_entpen | -0.31 |\n", + "| loss_vf_loss | 6.26e-10 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 31 |\n", + "| ev_tdlam_before | -0.293 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00411 |\n", + "| loss_pol_entpen | -0.31 |\n", + "| loss_vf_loss | 3.14e-10 |\n", + "| loss_kl | 0.000423 |\n", + "| loss_ent | 31 |\n", + "| ev_tdlam_before | -0.0744 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00386 |\n", + "| loss_pol_entpen | -0.31 |\n", + "| loss_vf_loss | 5.7e-09 |\n", + "| loss_kl | 0.00035 |\n", + "| loss_ent | 31 |\n", + "| ev_tdlam_before | -0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 436 |\n", + "| TimestepsSoFar | 6.28e+05 |\n", + "| TimeElapsed | 3.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.311 |\n", + "| loss_vf_loss | 6.22e-10 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 31.1 |\n", + "| ev_tdlam_before | -0.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00396 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 2.06e-09 |\n", + "| loss_kl | 0.00027 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00461 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 1.45e-09 |\n", + "| loss_kl | 0.000542 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.0813 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000794 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 5.04e-09 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00259 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 0.000166 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.381 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00274 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 5.38e-09 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.00117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 438 |\n", + "| TimestepsSoFar | 6.31e+05 |\n", + "| TimeElapsed | 3.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 9.3e-10 |\n", + "| loss_kl | 0.000438 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.076 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00401 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 5.9e-09 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.0471 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00243 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 4.5e-10 |\n", + "| loss_kl | 0.000289 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00345 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 6.71e-11 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0024 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 8.54e-10 |\n", + "| loss_kl | 0.000257 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | 0.00675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.312 |\n", + "| loss_vf_loss | 1.08e-09 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 31.2 |\n", + "| ev_tdlam_before | -0.119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 440 |\n", + "| TimestepsSoFar | 6.34e+05 |\n", + "| TimeElapsed | 3.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.313 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.000445 |\n", + "| loss_ent | 31.3 |\n", + "| ev_tdlam_before | 0.00942 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 442 |\n", + "| TimestepsSoFar | 6.36e+05 |\n", + "| TimeElapsed | 3.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000594 |\n", + "| loss_pol_entpen | -0.313 |\n", + "| loss_vf_loss | 9.6e-11 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 31.3 |\n", + "| ev_tdlam_before | -0.0565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 442 |\n", + "| TimestepsSoFar | 6.36e+05 |\n", + "| TimeElapsed | 3.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.313 |\n", + "| loss_vf_loss | 8.78e-11 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 31.3 |\n", + "| ev_tdlam_before | -0.000465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 442 |\n", + "| TimestepsSoFar | 6.36e+05 |\n", + "| TimeElapsed | 3.39e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.313 |\n", + "| loss_vf_loss | 9.86e-09 |\n", + "| loss_kl | 9.82e-05 |\n", + "| loss_ent | 31.3 |\n", + "| ev_tdlam_before | 5.53e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 442 |\n", + "| TimestepsSoFar | 6.36e+05 |\n", + "| TimeElapsed | 3.39e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.313 |\n", + "| loss_vf_loss | 6.69e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 31.3 |\n", + "| ev_tdlam_before | -0.131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 442 |\n", + "| TimestepsSoFar | 6.36e+05 |\n", + "| TimeElapsed | 3.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00578 |\n", + "| loss_pol_entpen | -0.314 |\n", + "| loss_vf_loss | 1.94e-09 |\n", + "| loss_kl | 0.000651 |\n", + "| loss_ent | 31.4 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00603 |\n", + "| loss_pol_entpen | -0.314 |\n", + "| loss_vf_loss | 2.07e-09 |\n", + "| loss_kl | 0.000772 |\n", + "| loss_ent | 31.4 |\n", + "| ev_tdlam_before | 0.00783 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00438 |\n", + "| loss_pol_entpen | -0.314 |\n", + "| loss_vf_loss | 6.16e-11 |\n", + "| loss_kl | 0.000439 |\n", + "| loss_ent | 31.4 |\n", + "| ev_tdlam_before | -0.0692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00776 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.000914 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.000553 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0027 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.000467 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.0303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 4.11e-09 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.00062 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 444 |\n", + "| TimestepsSoFar | 6.39e+05 |\n", + "| TimeElapsed | 3.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 9.4e-10 |\n", + "| loss_kl | 0.000255 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.0311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0044 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 2.82e-11 |\n", + "| loss_kl | 0.000421 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 3.21e-10 |\n", + "| loss_kl | 0.0002 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000433 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 7.17e-05 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 1.93e-09 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.0456 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00572 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 1.8e-09 |\n", + "| loss_kl | 0.000479 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 446 |\n", + "| TimestepsSoFar | 6.42e+05 |\n", + "| TimeElapsed | 3.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000634 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 9.15e-09 |\n", + "| loss_kl | 0.000119 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.0219 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.322 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00514 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 3.37e-09 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.0232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.315 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000498 |\n", + "| loss_ent | 31.5 |\n", + "| ev_tdlam_before | -0.253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00352 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 7.85e-09 |\n", + "| loss_kl | 0.000429 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | 0.00276 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.44e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000972 |\n", + "| loss_pol_entpen | -0.316 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 31.6 |\n", + "| ev_tdlam_before | -0.246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 448 |\n", + "| TimestepsSoFar | 6.45e+05 |\n", + "| TimeElapsed | 3.44e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.317 |\n", + "| loss_vf_loss | 3.66e-09 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 31.7 |\n", + "| ev_tdlam_before | -0.0015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 450 |\n", + "| TimestepsSoFar | 6.48e+05 |\n", + "| TimeElapsed | 3.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.317 |\n", + "| loss_vf_loss | 7.29e-11 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 31.7 |\n", + "| ev_tdlam_before | -0.0554 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 450 |\n", + "| TimestepsSoFar | 6.48e+05 |\n", + "| TimeElapsed | 3.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.317 |\n", + "| loss_vf_loss | 3.69e-09 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 31.7 |\n", + "| ev_tdlam_before | -0.165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 450 |\n", + "| TimestepsSoFar | 6.48e+05 |\n", + "| TimeElapsed | 3.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00548 |\n", + "| loss_pol_entpen | -0.317 |\n", + "| loss_vf_loss | 3.33e-09 |\n", + "| loss_kl | 0.000419 |\n", + "| loss_ent | 31.7 |\n", + "| ev_tdlam_before | -0.144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 450 |\n", + "| TimestepsSoFar | 6.48e+05 |\n", + "| TimeElapsed | 3.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.317 |\n", + "| loss_vf_loss | 8.01e-10 |\n", + "| loss_kl | 0.000357 |\n", + "| loss_ent | 31.7 |\n", + "| ev_tdlam_before | -0.0986 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 450 |\n", + "| TimestepsSoFar | 6.48e+05 |\n", + "| TimeElapsed | 3.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.318 |\n", + "| loss_vf_loss | 2.5e-09 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 31.8 |\n", + "| ev_tdlam_before | -0.0345 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.318 |\n", + "| loss_vf_loss | 1.85e-09 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 31.8 |\n", + "| ev_tdlam_before | -0.0792 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.318 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 31.8 |\n", + "| ev_tdlam_before | -0.0488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00482 |\n", + "| loss_pol_entpen | -0.318 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 31.8 |\n", + "| ev_tdlam_before | -0.103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00893 |\n", + "| loss_pol_entpen | -0.319 |\n", + "| loss_vf_loss | 1.58e-09 |\n", + "| loss_kl | 0.00093 |\n", + "| loss_ent | 31.9 |\n", + "| ev_tdlam_before | -0.064 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0081 |\n", + "| loss_pol_entpen | -0.319 |\n", + "| loss_vf_loss | 9.71e-10 |\n", + "| loss_kl | 0.000947 |\n", + "| loss_ent | 31.9 |\n", + "| ev_tdlam_before | -0.251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 452 |\n", + "| TimestepsSoFar | 6.51e+05 |\n", + "| TimeElapsed | 3.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00308 |\n", + "| loss_pol_entpen | -0.32 |\n", + "| loss_vf_loss | 1.33e-08 |\n", + "| loss_kl | 0.000351 |\n", + "| loss_ent | 32 |\n", + "| ev_tdlam_before | -0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.002 |\n", + "| loss_pol_entpen | -0.32 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.000247 |\n", + "| loss_ent | 32 |\n", + "| ev_tdlam_before | -0.634 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00667 |\n", + "| loss_pol_entpen | -0.321 |\n", + "| loss_vf_loss | 8.92e-11 |\n", + "| loss_kl | 0.000514 |\n", + "| loss_ent | 32.1 |\n", + "| ev_tdlam_before | -0.0199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00294 |\n", + "| loss_pol_entpen | -0.321 |\n", + "| loss_vf_loss | 8.85e-11 |\n", + "| loss_kl | 0.000551 |\n", + "| loss_ent | 32.1 |\n", + "| ev_tdlam_before | -0.00269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00587 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 3.93e-10 |\n", + "| loss_kl | 0.000534 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | -0.00227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00799 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 0.000992 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | -0.00361 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 454 |\n", + "| TimestepsSoFar | 6.54e+05 |\n", + "| TimeElapsed | 3.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00542 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 7.52e-09 |\n", + "| loss_kl | 0.000523 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | -3.71e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.49e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00767 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 2.62e-10 |\n", + "| loss_kl | 0.000919 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | -0.214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.49e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 1.87e-09 |\n", + "| loss_kl | 0.00029 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | 0.000818 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 1.15e-09 |\n", + "| loss_kl | 0.000255 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | -0.103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00629 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 9.28e-09 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | -0.0206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00968 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 4.28e-09 |\n", + "| loss_kl | 0.00108 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | -1.73 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 456 |\n", + "| TimestepsSoFar | 6.57e+05 |\n", + "| TimeElapsed | 3.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.322 |\n", + "| loss_vf_loss | 7.74e-10 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 32.2 |\n", + "| ev_tdlam_before | 0.000657 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 458 |\n", + "| TimestepsSoFar | 6.6e+05 |\n", + "| TimeElapsed | 3.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00727 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000624 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | 0.00858 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 458 |\n", + "| TimestepsSoFar | 6.6e+05 |\n", + "| TimeElapsed | 3.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0047 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 7.04e-10 |\n", + "| loss_kl | 0.000563 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | -0.174 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 458 |\n", + "| TimestepsSoFar | 6.6e+05 |\n", + "| TimeElapsed | 3.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000232 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 458 |\n", + "| TimestepsSoFar | 6.6e+05 |\n", + "| TimeElapsed | 3.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.323 |\n", + "| loss_vf_loss | 1.72e-09 |\n", + "| loss_kl | 0.000204 |\n", + "| loss_ent | 32.3 |\n", + "| ev_tdlam_before | -0.0251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 458 |\n", + "| TimestepsSoFar | 6.6e+05 |\n", + "| TimeElapsed | 3.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0046 |\n", + "| loss_pol_entpen | -0.324 |\n", + "| loss_vf_loss | 9.76e-10 |\n", + "| loss_kl | 0.000733 |\n", + "| loss_ent | 32.4 |\n", + "| ev_tdlam_before | -0.00841 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00308 |\n", + "| loss_pol_entpen | -0.324 |\n", + "| loss_vf_loss | 1.55e-09 |\n", + "| loss_kl | 0.000377 |\n", + "| loss_ent | 32.4 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00473 |\n", + "| loss_pol_entpen | -0.324 |\n", + "| loss_vf_loss | 8.86e-09 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 32.4 |\n", + "| ev_tdlam_before | -0.0702 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 3.8e-10 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 3.65e-09 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.0461 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00336 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 2.41e-10 |\n", + "| loss_kl | 0.000327 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.446 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 460 |\n", + "| TimestepsSoFar | 6.62e+05 |\n", + "| TimeElapsed | 3.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00548 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 3.54e-10 |\n", + "| loss_kl | 0.000559 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.0502 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00442 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 6.75e-10 |\n", + "| loss_kl | 0.000455 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | 0.00169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 0.000259 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | 0.00322 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 7.12e-09 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | 0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 7.53e-11 |\n", + "| loss_kl | 0.000258 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.597 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000953 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.00522 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000264 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 462 |\n", + "| TimestepsSoFar | 6.65e+05 |\n", + "| TimeElapsed | 3.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 2.4e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.0471 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00724 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000678 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 9.48e-11 |\n", + "| loss_kl | 0.000326 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | 0.00564 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00228 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | 0.00746 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00246 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 5.97e-10 |\n", + "| loss_kl | 0.000221 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 2.11e-09 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.068 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 464 |\n", + "| TimestepsSoFar | 6.68e+05 |\n", + "| TimeElapsed | 3.56e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000694 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 8.57e-11 |\n", + "| loss_kl | 9.97e-05 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.0335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 466 |\n", + "| TimestepsSoFar | 6.71e+05 |\n", + "| TimeElapsed | 3.57e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.325 |\n", + "| loss_vf_loss | 8.1e-10 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 32.5 |\n", + "| ev_tdlam_before | -0.0129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 466 |\n", + "| TimestepsSoFar | 6.71e+05 |\n", + "| TimeElapsed | 3.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.85e-09 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 466 |\n", + "| TimestepsSoFar | 6.71e+05 |\n", + "| TimeElapsed | 3.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00387 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.08e-09 |\n", + "| loss_kl | 0.000411 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.0235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 466 |\n", + "| TimestepsSoFar | 6.71e+05 |\n", + "| TimeElapsed | 3.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00186 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.83e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 466 |\n", + "| TimestepsSoFar | 6.71e+05 |\n", + "| TimeElapsed | 3.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00471 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 3.13e-10 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.000322 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.58e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.326 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 0.000285 |\n", + "| loss_ent | 32.6 |\n", + "| ev_tdlam_before | -0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00409 |\n", + "| loss_pol_entpen | -0.327 |\n", + "| loss_vf_loss | 2.46e-09 |\n", + "| loss_kl | 0.000355 |\n", + "| loss_ent | 32.7 |\n", + "| ev_tdlam_before | -0.0277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00477 |\n", + "| loss_pol_entpen | -0.327 |\n", + "| loss_vf_loss | 4.81e-10 |\n", + "| loss_kl | 0.000439 |\n", + "| loss_ent | 32.7 |\n", + "| ev_tdlam_before | -0.18 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00447 |\n", + "| loss_pol_entpen | -0.327 |\n", + "| loss_vf_loss | 2.4e-10 |\n", + "| loss_kl | 0.00055 |\n", + "| loss_ent | 32.7 |\n", + "| ev_tdlam_before | -0.0226 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.59e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00327 |\n", + "| loss_pol_entpen | -0.327 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000334 |\n", + "| loss_ent | 32.7 |\n", + "| ev_tdlam_before | -0.000538 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 468 |\n", + "| TimestepsSoFar | 6.74e+05 |\n", + "| TimeElapsed | 3.59e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00479 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 2.4e-10 |\n", + "| loss_kl | 0.000562 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | 1.22e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000924 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 2.97e-10 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | -0.00175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | -0.0318 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00381 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 1.26e-09 |\n", + "| loss_kl | 0.000324 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | -0.0479 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 6.16e-10 |\n", + "| loss_kl | 0.00022 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | -0.0389 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000619 |\n", + "| loss_pol_entpen | -0.328 |\n", + "| loss_vf_loss | 5.22e-11 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 32.8 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 470 |\n", + "| TimestepsSoFar | 6.77e+05 |\n", + "| TimeElapsed | 3.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.329 |\n", + "| loss_vf_loss | 6.29e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 32.9 |\n", + "| ev_tdlam_before | -0.00281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.329 |\n", + "| loss_vf_loss | 5.62e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 32.9 |\n", + "| ev_tdlam_before | -0.0231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00195 |\n", + "| loss_pol_entpen | -0.329 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 32.9 |\n", + "| ev_tdlam_before | -0.00768 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.33 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000119 |\n", + "| loss_ent | 33 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00419 |\n", + "| loss_pol_entpen | -0.33 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 0.000403 |\n", + "| loss_ent | 33 |\n", + "| ev_tdlam_before | -0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00791 |\n", + "| loss_pol_entpen | -0.33 |\n", + "| loss_vf_loss | 3.06e-10 |\n", + "| loss_kl | 0.000731 |\n", + "| loss_ent | 33 |\n", + "| ev_tdlam_before | -0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 472 |\n", + "| TimestepsSoFar | 6.8e+05 |\n", + "| TimeElapsed | 3.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0064 |\n", + "| loss_pol_entpen | -0.331 |\n", + "| loss_vf_loss | 1.87e-09 |\n", + "| loss_kl | 0.000465 |\n", + "| loss_ent | 33.1 |\n", + "| ev_tdlam_before | -0.00923 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 474 |\n", + "| TimestepsSoFar | 6.83e+05 |\n", + "| TimeElapsed | 3.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00383 |\n", + "| loss_pol_entpen | -0.331 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.000325 |\n", + "| loss_ent | 33.1 |\n", + "| ev_tdlam_before | -0.032 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 474 |\n", + "| TimestepsSoFar | 6.83e+05 |\n", + "| TimeElapsed | 3.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0016 |\n", + "| loss_pol_entpen | -0.331 |\n", + "| loss_vf_loss | 4.07e-10 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 33.1 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 474 |\n", + "| TimestepsSoFar | 6.83e+05 |\n", + "| TimeElapsed | 3.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00796 |\n", + "| loss_pol_entpen | -0.331 |\n", + "| loss_vf_loss | 3.03e-10 |\n", + "| loss_kl | 0.000565 |\n", + "| loss_ent | 33.1 |\n", + "| ev_tdlam_before | -0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 474 |\n", + "| TimestepsSoFar | 6.83e+05 |\n", + "| TimeElapsed | 3.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.331 |\n", + "| loss_vf_loss | 2.32e-09 |\n", + "| loss_kl | 0.000336 |\n", + "| loss_ent | 33.1 |\n", + "| ev_tdlam_before | -0.00442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000267 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 474 |\n", + "| TimestepsSoFar | 6.83e+05 |\n", + "| TimeElapsed | 3.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00214 |\n", + "| loss_pol_entpen | -0.332 |\n", + "| loss_vf_loss | 1.97e-09 |\n", + "| loss_kl | 0.00018 |\n", + "| loss_ent | 33.2 |\n", + "| ev_tdlam_before | -0.000957 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.332 |\n", + "| loss_vf_loss | 7.63e-10 |\n", + "| loss_kl | 0.000346 |\n", + "| loss_ent | 33.2 |\n", + "| ev_tdlam_before | 0.000291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.332 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0.000306 |\n", + "| loss_ent | 33.2 |\n", + "| ev_tdlam_before | -0.135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.332 |\n", + "| loss_vf_loss | 5.82e-10 |\n", + "| loss_kl | 0.000391 |\n", + "| loss_ent | 33.2 |\n", + "| ev_tdlam_before | -0.039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.333 |\n", + "| loss_vf_loss | 4.17e-09 |\n", + "| loss_kl | 0.000342 |\n", + "| loss_ent | 33.3 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00278 |\n", + "| loss_pol_entpen | -0.333 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 33.3 |\n", + "| ev_tdlam_before | -0.35 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000266 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 476 |\n", + "| TimestepsSoFar | 6.85e+05 |\n", + "| TimeElapsed | 3.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00418 |\n", + "| loss_pol_entpen | -0.333 |\n", + "| loss_vf_loss | 6.59e-10 |\n", + "| loss_kl | 0.000346 |\n", + "| loss_ent | 33.3 |\n", + "| ev_tdlam_before | 0.00533 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 3.82e-10 |\n", + "| loss_kl | 0.000433 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0433 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00424 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 8.79e-10 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 9.61e-11 |\n", + "| loss_kl | 0.000241 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.00647 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00777 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 5.77e-11 |\n", + "| loss_kl | 0.000625 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | 0.00734 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 0.000524 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0268 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000257 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 478 |\n", + "| TimestepsSoFar | 6.88e+05 |\n", + "| TimeElapsed | 3.67e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000448 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00425 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 0.000323 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0196 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 9.52e-10 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 2.31e-09 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0349 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000621 |\n", + "| loss_pol_entpen | -0.334 |\n", + "| loss_vf_loss | 3.4e-10 |\n", + "| loss_kl | 7.67e-05 |\n", + "| loss_ent | 33.4 |\n", + "| ev_tdlam_before | -0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 480 |\n", + "| TimestepsSoFar | 6.91e+05 |\n", + "| TimeElapsed | 3.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00724 |\n", + "| loss_pol_entpen | -0.335 |\n", + "| loss_vf_loss | 2.19e-09 |\n", + "| loss_kl | 0.000594 |\n", + "| loss_ent | 33.5 |\n", + "| ev_tdlam_before | -0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 482 |\n", + "| TimestepsSoFar | 6.94e+05 |\n", + "| TimeElapsed | 3.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.335 |\n", + "| loss_vf_loss | 1.52e-09 |\n", + "| loss_kl | 0.000507 |\n", + "| loss_ent | 33.5 |\n", + "| ev_tdlam_before | -0.163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 482 |\n", + "| TimestepsSoFar | 6.94e+05 |\n", + "| TimeElapsed | 3.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.335 |\n", + "| loss_vf_loss | 3.32e-09 |\n", + "| loss_kl | 0.000339 |\n", + "| loss_ent | 33.5 |\n", + "| ev_tdlam_before | -0.0994 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 482 |\n", + "| TimestepsSoFar | 6.94e+05 |\n", + "| TimeElapsed | 3.69e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00426 |\n", + "| loss_pol_entpen | -0.335 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 0.000394 |\n", + "| loss_ent | 33.5 |\n", + "| ev_tdlam_before | -0.0527 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 482 |\n", + "| TimestepsSoFar | 6.94e+05 |\n", + "| TimeElapsed | 3.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00649 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 0.000434 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | 0.000383 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 482 |\n", + "| TimestepsSoFar | 6.94e+05 |\n", + "| TimeElapsed | 3.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00459 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.000516 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0494 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 6.8e-10 |\n", + "| loss_kl | 0.000397 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00333 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 8.03e-10 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0215 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 8.6e-10 |\n", + "| loss_kl | 0.000288 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 1.2e-09 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0605 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 8.49e-11 |\n", + "| loss_kl | 0.000258 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0521 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 484 |\n", + "| TimestepsSoFar | 6.97e+05 |\n", + "| TimeElapsed | 3.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 1.47e-09 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 8.15e-10 |\n", + "| loss_kl | 9.97e-05 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00269 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | -0.0346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0048 |\n", + "| loss_pol_entpen | -0.336 |\n", + "| loss_vf_loss | 6.03e-10 |\n", + "| loss_kl | 0.000426 |\n", + "| loss_ent | 33.6 |\n", + "| ev_tdlam_before | 0.00301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00312 |\n", + "| loss_pol_entpen | -0.337 |\n", + "| loss_vf_loss | 1.77e-09 |\n", + "| loss_kl | 0.000424 |\n", + "| loss_ent | 33.7 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00341 |\n", + "| loss_pol_entpen | -0.337 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 0.000294 |\n", + "| loss_ent | 33.7 |\n", + "| ev_tdlam_before | -0.00892 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 486 |\n", + "| TimestepsSoFar | 7e+05 |\n", + "| TimeElapsed | 3.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000389 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.00872 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.000359 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.000108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 1.18e-09 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.0173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000841 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.0218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00541 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000311 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.0376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00464 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 8.74e-10 |\n", + "| loss_kl | 0.000487 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -3.7e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000269 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 488 |\n", + "| TimestepsSoFar | 7.03e+05 |\n", + "| TimeElapsed | 3.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00521 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 3.32e-10 |\n", + "| loss_kl | 0.000379 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.000399 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 490 |\n", + "| TimestepsSoFar | 7.06e+05 |\n", + "| TimeElapsed | 3.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.66e-05 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 1.14e-09 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.0525 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 490 |\n", + "| TimestepsSoFar | 7.06e+05 |\n", + "| TimeElapsed | 3.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00298 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 0.000246 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.0301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 490 |\n", + "| TimestepsSoFar | 7.06e+05 |\n", + "| TimeElapsed | 3.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00368 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 1.5e-09 |\n", + "| loss_kl | 0.000288 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.037 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 490 |\n", + "| TimestepsSoFar | 7.06e+05 |\n", + "| TimeElapsed | 3.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00245 |\n", + "| loss_pol_entpen | -0.338 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000246 |\n", + "| loss_ent | 33.8 |\n", + "| ev_tdlam_before | -0.16 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00026 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 490 |\n", + "| TimestepsSoFar | 7.06e+05 |\n", + "| TimeElapsed | 3.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.002 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 3.5e-11 |\n", + "| loss_kl | 0.000228 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.0402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.00046 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 5.64e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.0775 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 9.15e-11 |\n", + "| loss_kl | 0.000304 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.0796 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00426 |\n", + "| loss_pol_entpen | -0.339 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.00036 |\n", + "| loss_ent | 33.9 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00682 |\n", + "| loss_pol_entpen | -0.34 |\n", + "| loss_vf_loss | 3.95e-10 |\n", + "| loss_kl | 0.000635 |\n", + "| loss_ent | 34 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 492 |\n", + "| TimestepsSoFar | 7.08e+05 |\n", + "| TimeElapsed | 3.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 7.64e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.0356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00572 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 1.05e-09 |\n", + "| loss_kl | 0.00048 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00644 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 9.36e-11 |\n", + "| loss_kl | 0.000737 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00438 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 0.000317 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.00204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0087 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 0.000783 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.00202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00559 |\n", + "| loss_pol_entpen | -0.341 |\n", + "| loss_vf_loss | 4.48e-10 |\n", + "| loss_kl | 0.000744 |\n", + "| loss_ent | 34.1 |\n", + "| ev_tdlam_before | -0.00706 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 494 |\n", + "| TimestepsSoFar | 7.11e+05 |\n", + "| TimeElapsed | 3.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000304 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 4e-05 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | -0.0914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000747 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 5.81e-05 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | 8.61e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 7.27e-10 |\n", + "| loss_kl | 7.19e-05 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | 0.00051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 2.44e-09 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | -0.0136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 3.45e-09 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | -0.317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00362 |\n", + "| loss_pol_entpen | -0.342 |\n", + "| loss_vf_loss | 4.56e-10 |\n", + "| loss_kl | 0.000375 |\n", + "| loss_ent | 34.2 |\n", + "| ev_tdlam_before | -0.0942 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 496 |\n", + "| TimestepsSoFar | 7.14e+05 |\n", + "| TimeElapsed | 3.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 1.7e-09 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.0158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 498 |\n", + "| TimestepsSoFar | 7.17e+05 |\n", + "| TimeElapsed | 3.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 3.94e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.0199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 498 |\n", + "| TimestepsSoFar | 7.17e+05 |\n", + "| TimeElapsed | 3.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00738 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000601 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.0715 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 498 |\n", + "| TimestepsSoFar | 7.17e+05 |\n", + "| TimeElapsed | 3.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00425 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.000449 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | 0.00668 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 498 |\n", + "| TimestepsSoFar | 7.17e+05 |\n", + "| TimeElapsed | 3.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 2.44e-10 |\n", + "| loss_kl | 0.000325 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | 0.0136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 498 |\n", + "| TimestepsSoFar | 7.17e+05 |\n", + "| TimeElapsed | 3.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.0928 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 3.57e-10 |\n", + "| loss_kl | 0.00021 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.000506 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00243 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 2.35e-11 |\n", + "| loss_kl | 0.000273 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 3.3e-10 |\n", + "| loss_kl | 0.000248 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00259 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 1.83e-09 |\n", + "| loss_kl | 0.000318 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00335 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 4.93e-10 |\n", + "| loss_kl | 0.000304 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 500 |\n", + "| TimestepsSoFar | 7.2e+05 |\n", + "| TimeElapsed | 3.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000374 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 9.4e-10 |\n", + "| loss_kl | 5.24e-05 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.00174 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.84e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000298 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 4.15e-10 |\n", + "| loss_kl | 1.84e-05 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.0228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00325 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 1.15e-09 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.0254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.85e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00445 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 0.000273 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00739 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 0.000738 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -1.91e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 6.78e-10 |\n", + "| loss_kl | 0.000367 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.00192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 502 |\n", + "| TimestepsSoFar | 7.23e+05 |\n", + "| TimeElapsed | 3.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 8e-11 |\n", + "| loss_kl | 0.00018 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.0173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00399 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 3.83e-11 |\n", + "| loss_kl | 0.000334 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | -0.00276 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00314 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 3.69e-10 |\n", + "| loss_kl | 0.000233 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | 0.00152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.343 |\n", + "| loss_vf_loss | 6.76e-11 |\n", + "| loss_kl | 0.00039 |\n", + "| loss_ent | 34.3 |\n", + "| ev_tdlam_before | 0.0163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00782 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 1.23e-09 |\n", + "| loss_kl | 0.000703 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | 7.21e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.344 |\n", + "| loss_vf_loss | 8.95e-10 |\n", + "| loss_kl | 0.000307 |\n", + "| loss_ent | 34.4 |\n", + "| ev_tdlam_before | -0.0348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 504 |\n", + "| TimestepsSoFar | 7.26e+05 |\n", + "| TimeElapsed | 3.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 7.28e-11 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 506 |\n", + "| TimestepsSoFar | 7.29e+05 |\n", + "| TimeElapsed | 3.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | 0.00231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 506 |\n", + "| TimestepsSoFar | 7.29e+05 |\n", + "| TimeElapsed | 3.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 506 |\n", + "| TimestepsSoFar | 7.29e+05 |\n", + "| TimeElapsed | 3.88e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 7.13e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.000493 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 506 |\n", + "| TimestepsSoFar | 7.29e+05 |\n", + "| TimeElapsed | 3.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 4.03e-10 |\n", + "| loss_kl | 6.47e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | 0.000359 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 506 |\n", + "| TimestepsSoFar | 7.29e+05 |\n", + "| TimeElapsed | 3.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00489 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 3.53e-10 |\n", + "| loss_kl | 0.000311 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | 0.00408 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00454 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 3.17e-10 |\n", + "| loss_kl | 0.000498 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.0191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.89e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000207 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 1.82e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00307 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 2.29e-09 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.000491 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.89e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 7.49e-10 |\n", + "| loss_kl | 0.000206 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.89e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000339 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 4.53e-09 |\n", + "| loss_kl | 6.5e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.0224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 508 |\n", + "| TimestepsSoFar | 7.32e+05 |\n", + "| TimeElapsed | 3.9e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000122 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 9.78e-10 |\n", + "| loss_kl | 7.25e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | 0.000896 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.345 |\n", + "| loss_vf_loss | 3.49e-10 |\n", + "| loss_kl | 8.65e-05 |\n", + "| loss_ent | 34.5 |\n", + "| ev_tdlam_before | -0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 7.4e-10 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.0176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00269 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 5.75e-10 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.00509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 4.07e-10 |\n", + "| loss_kl | 0.000318 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00373 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 1.16e-09 |\n", + "| loss_kl | 0.000356 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 510 |\n", + "| TimestepsSoFar | 7.34e+05 |\n", + "| TimeElapsed | 3.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00507 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 4.26e-10 |\n", + "| loss_kl | 0.00035 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | 0.00229 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00342 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 2.67e-10 |\n", + "| loss_kl | 0.000445 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00816 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 0.000683 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00245 |\n", + "| loss_pol_entpen | -0.346 |\n", + "| loss_vf_loss | 8.05e-10 |\n", + "| loss_kl | 0.000392 |\n", + "| loss_ent | 34.6 |\n", + "| ev_tdlam_before | 0.000467 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00473 |\n", + "| loss_pol_entpen | -0.347 |\n", + "| loss_vf_loss | 7.91e-10 |\n", + "| loss_kl | 0.000348 |\n", + "| loss_ent | 34.7 |\n", + "| ev_tdlam_before | -0.0353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00498 |\n", + "| loss_pol_entpen | -0.347 |\n", + "| loss_vf_loss | 8.31e-10 |\n", + "| loss_kl | 0.000577 |\n", + "| loss_ent | 34.7 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 512 |\n", + "| TimestepsSoFar | 7.37e+05 |\n", + "| TimeElapsed | 3.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 9.03e-10 |\n", + "| loss_kl | 0.000206 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 514 |\n", + "| TimestepsSoFar | 7.4e+05 |\n", + "| TimeElapsed | 3.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00168 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 4.61e-09 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 514 |\n", + "| TimestepsSoFar | 7.4e+05 |\n", + "| TimeElapsed | 3.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00649 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 2.95e-10 |\n", + "| loss_kl | 0.000518 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 514 |\n", + "| TimestepsSoFar | 7.4e+05 |\n", + "| TimeElapsed | 3.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000258 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 5.08e-11 |\n", + "| loss_kl | 0.000189 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | 0.00392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 514 |\n", + "| TimestepsSoFar | 7.4e+05 |\n", + "| TimeElapsed | 3.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 2.98e-10 |\n", + "| loss_kl | 0.000168 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.000592 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 514 |\n", + "| TimestepsSoFar | 7.4e+05 |\n", + "| TimeElapsed | 3.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00275 |\n", + "| loss_pol_entpen | -0.349 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 34.9 |\n", + "| ev_tdlam_before | 0.00354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.95e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00348 |\n", + "| loss_pol_entpen | -0.349 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 0.000353 |\n", + "| loss_ent | 34.9 |\n", + "| ev_tdlam_before | -0.0183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.349 |\n", + "| loss_vf_loss | 5.38e-11 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 34.9 |\n", + "| ev_tdlam_before | 0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.349 |\n", + "| loss_vf_loss | 6.6e-10 |\n", + "| loss_kl | 0.000333 |\n", + "| loss_ent | 34.9 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0045 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 0.000436 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.0281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00431 |\n", + "| loss_pol_entpen | -0.348 |\n", + "| loss_vf_loss | 7.24e-11 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 34.8 |\n", + "| ev_tdlam_before | -0.00918 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 516 |\n", + "| TimestepsSoFar | 7.43e+05 |\n", + "| TimeElapsed | 3.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00392 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 2.41e-09 |\n", + "| loss_kl | 0.000455 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | -0.0653 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.34e-05 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 5.91e-05 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | -0.11 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.97e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00298 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000183 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | 0.0017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 7.4e-11 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | -0.00274 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00421 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 6.33e-11 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | 0.000778 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.97e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000798 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 6.4e-10 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 518 |\n", + "| TimestepsSoFar | 7.46e+05 |\n", + "| TimeElapsed | 3.97e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00365 |\n", + "| loss_pol_entpen | -0.35 |\n", + "| loss_vf_loss | 2.42e-10 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 35 |\n", + "| ev_tdlam_before | -0.09 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00441 |\n", + "| loss_pol_entpen | -0.351 |\n", + "| loss_vf_loss | 2.17e-10 |\n", + "| loss_kl | 0.000456 |\n", + "| loss_ent | 35.1 |\n", + "| ev_tdlam_before | -0.0046 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000168 |\n", + "| loss_pol_entpen | -0.351 |\n", + "| loss_vf_loss | 2.06e-10 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 35.1 |\n", + "| ev_tdlam_before | -0.00584 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00287 |\n", + "| loss_pol_entpen | -0.351 |\n", + "| loss_vf_loss | 9.28e-11 |\n", + "| loss_kl | 0.000226 |\n", + "| loss_ent | 35.1 |\n", + "| ev_tdlam_before | -0.026 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.98e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000511 |\n", + "| loss_pol_entpen | -0.351 |\n", + "| loss_vf_loss | 2.13e-10 |\n", + "| loss_kl | 8.06e-05 |\n", + "| loss_ent | 35.1 |\n", + "| ev_tdlam_before | 0.00565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000895 |\n", + "| loss_pol_entpen | -0.351 |\n", + "| loss_vf_loss | 3.31e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 35.1 |\n", + "| ev_tdlam_before | -0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 520 |\n", + "| TimestepsSoFar | 7.49e+05 |\n", + "| TimeElapsed | 3.99e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00314 |\n", + "| loss_pol_entpen | -0.352 |\n", + "| loss_vf_loss | 5.79e-10 |\n", + "| loss_kl | 0.000334 |\n", + "| loss_ent | 35.2 |\n", + "| ev_tdlam_before | -0.00893 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 522 |\n", + "| TimestepsSoFar | 7.52e+05 |\n", + "| TimeElapsed | 4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00196 |\n", + "| loss_pol_entpen | -0.352 |\n", + "| loss_vf_loss | 8.13e-11 |\n", + "| loss_kl | 0.000196 |\n", + "| loss_ent | 35.2 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 522 |\n", + "| TimestepsSoFar | 7.52e+05 |\n", + "| TimeElapsed | 4e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 6.18e-10 |\n", + "| loss_kl | 0.000176 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | 0.000777 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 522 |\n", + "| TimestepsSoFar | 7.52e+05 |\n", + "| TimeElapsed | 4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.352 |\n", + "| loss_vf_loss | 7.87e-11 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 35.2 |\n", + "| ev_tdlam_before | 0.00196 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 522 |\n", + "| TimestepsSoFar | 7.52e+05 |\n", + "| TimeElapsed | 4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00621 |\n", + "| loss_pol_entpen | -0.352 |\n", + "| loss_vf_loss | 2.42e-10 |\n", + "| loss_kl | 0.000512 |\n", + "| loss_ent | 35.2 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 522 |\n", + "| TimestepsSoFar | 7.52e+05 |\n", + "| TimeElapsed | 4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000663 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 1.02e-09 |\n", + "| loss_kl | 8.51e-05 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | -0.000104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | -0.102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 5.74e-11 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 1.83e-10 |\n", + "| loss_kl | 0.000213 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | 0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 8.82e-05 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | 0.00791 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.353 |\n", + "| loss_vf_loss | 6.83e-10 |\n", + "| loss_kl | 9.24e-05 |\n", + "| loss_ent | 35.3 |\n", + "| ev_tdlam_before | -0.0223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 524 |\n", + "| TimestepsSoFar | 7.55e+05 |\n", + "| TimeElapsed | 4.02e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 2.38e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -8.86e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00269 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 1.11e-09 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -0.0192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00421 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 2.25e-09 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -0.112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00417 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 4.21e-10 |\n", + "| loss_kl | 0.000328 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -0.0956 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 2.59e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -0.0399 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.354 |\n", + "| loss_vf_loss | 7.9e-11 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 35.4 |\n", + "| ev_tdlam_before | -0.00813 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 526 |\n", + "| TimestepsSoFar | 7.57e+05 |\n", + "| TimeElapsed | 4.03e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000196 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 3.39e-09 |\n", + "| loss_kl | 3.06e-05 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | -0.00964 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000631 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 2.55e-10 |\n", + "| loss_kl | 6.6e-05 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | -0.351 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.04e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | 0.0227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 5.12e-10 |\n", + "| loss_kl | 0.000177 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | -0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.04e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 9.32e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | -0.0678 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000971 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 9.71e-05 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | -0.115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 528 |\n", + "| TimestepsSoFar | 7.6e+05 |\n", + "| TimeElapsed | 4.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00196 |\n", + "| loss_pol_entpen | -0.355 |\n", + "| loss_vf_loss | 3.39e-10 |\n", + "| loss_kl | 0.000264 |\n", + "| loss_ent | 35.5 |\n", + "| ev_tdlam_before | 0.000302 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 530 |\n", + "| TimestepsSoFar | 7.63e+05 |\n", + "| TimeElapsed | 4.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.356 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.000111 |\n", + "| loss_ent | 35.6 |\n", + "| ev_tdlam_before | -0.0536 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 530 |\n", + "| TimestepsSoFar | 7.63e+05 |\n", + "| TimeElapsed | 4.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00157 |\n", + "| loss_pol_entpen | -0.356 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 0.000209 |\n", + "| loss_ent | 35.6 |\n", + "| ev_tdlam_before | 0.00161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 530 |\n", + "| TimestepsSoFar | 7.63e+05 |\n", + "| TimeElapsed | 4.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0024 |\n", + "| loss_pol_entpen | -0.356 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 35.6 |\n", + "| ev_tdlam_before | -0.00853 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 530 |\n", + "| TimestepsSoFar | 7.63e+05 |\n", + "| TimeElapsed | 4.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00515 |\n", + "| loss_pol_entpen | -0.356 |\n", + "| loss_vf_loss | 7.95e-11 |\n", + "| loss_kl | 0.000477 |\n", + "| loss_ent | 35.6 |\n", + "| ev_tdlam_before | 0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 530 |\n", + "| TimestepsSoFar | 7.63e+05 |\n", + "| TimeElapsed | 4.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00297 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 9.32e-10 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.00173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 1.07e-09 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0833 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.07e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000927 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 8.91e-11 |\n", + "| loss_kl | 3.84e-05 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0833 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.07e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000763 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 5.9e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | 0.000883 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00325 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 9.56e-10 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | 0.00703 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000632 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 2.37e-10 |\n", + "| loss_kl | 3.18e-05 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.00613 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 532 |\n", + "| TimestepsSoFar | 7.66e+05 |\n", + "| TimeElapsed | 4.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0052 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 6.01e-10 |\n", + "| loss_kl | 0.000485 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0039 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 5.92e-10 |\n", + "| loss_kl | 0.000552 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00282 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 6.99e-10 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 4e-09 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000595 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 5.7e-10 |\n", + "| loss_kl | 7.01e-05 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00229 |\n", + "| loss_pol_entpen | -0.357 |\n", + "| loss_vf_loss | 6.92e-11 |\n", + "| loss_kl | 0.000158 |\n", + "| loss_ent | 35.7 |\n", + "| ev_tdlam_before | -0.0517 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 534 |\n", + "| TimestepsSoFar | 7.69e+05 |\n", + "| TimeElapsed | 4.09e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000305 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.00576 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00331 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 2.47e-10 |\n", + "| loss_kl | 0.000417 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.0313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.1e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00458 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000413 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.000161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 4.35e-10 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.0154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00275 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 3.53e-10 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.0527 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000303 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 536 |\n", + "| TimestepsSoFar | 7.72e+05 |\n", + "| TimeElapsed | 4.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00662 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 5.59e-10 |\n", + "| loss_kl | 0.00056 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | 0.00414 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 538 |\n", + "| TimestepsSoFar | 7.75e+05 |\n", + "| TimeElapsed | 4.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | 0.000121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 538 |\n", + "| TimestepsSoFar | 7.75e+05 |\n", + "| TimeElapsed | 4.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.00291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 538 |\n", + "| TimestepsSoFar | 7.75e+05 |\n", + "| TimeElapsed | 4.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00222 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 1.07e-09 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.00699 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 538 |\n", + "| TimestepsSoFar | 7.75e+05 |\n", + "| TimeElapsed | 4.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00308 |\n", + "| loss_pol_entpen | -0.358 |\n", + "| loss_vf_loss | 6.06e-11 |\n", + "| loss_kl | 0.000289 |\n", + "| loss_ent | 35.8 |\n", + "| ev_tdlam_before | -0.183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 538 |\n", + "| TimestepsSoFar | 7.75e+05 |\n", + "| TimeElapsed | 4.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.359 |\n", + "| loss_vf_loss | 3.05e-10 |\n", + "| loss_kl | 0.000293 |\n", + "| loss_ent | 35.9 |\n", + "| ev_tdlam_before | 0.00238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000952 |\n", + "| loss_pol_entpen | -0.359 |\n", + "| loss_vf_loss | 8.15e-11 |\n", + "| loss_kl | 0.000165 |\n", + "| loss_ent | 35.9 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.13e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.359 |\n", + "| loss_vf_loss | 3.84e-10 |\n", + "| loss_kl | 0.000308 |\n", + "| loss_ent | 35.9 |\n", + "| ev_tdlam_before | -0.000709 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00127 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000196 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.0549 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 2.93e-10 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.00219 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 9.08e-11 |\n", + "| loss_kl | 0.000359 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 540 |\n", + "| TimestepsSoFar | 7.78e+05 |\n", + "| TimeElapsed | 4.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.00725 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.005 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 5.71e-11 |\n", + "| loss_kl | 0.000296 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00047 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 0.000128 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.00678 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00521 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 5.04e-10 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.0179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0052 |\n", + "| loss_pol_entpen | -0.36 |\n", + "| loss_vf_loss | 8.69e-10 |\n", + "| loss_kl | 0.000629 |\n", + "| loss_ent | 36 |\n", + "| ev_tdlam_before | -0.0255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000111 |\n", + "| loss_pol_entpen | -0.361 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 8.36e-05 |\n", + "| loss_ent | 36.1 |\n", + "| ev_tdlam_before | -0.0983 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 542 |\n", + "| TimestepsSoFar | 7.8e+05 |\n", + "| TimeElapsed | 4.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000471 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 6.69e-10 |\n", + "| loss_kl | 5.6e-05 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.000772 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000837 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.00235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.00628 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00156 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 7.71e-11 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 3.2e-10 |\n", + "| loss_kl | 0.000147 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | 0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00248 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 8.8e-11 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.0293 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 544 |\n", + "| TimestepsSoFar | 7.83e+05 |\n", + "| TimeElapsed | 4.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00385 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 7.58e-10 |\n", + "| loss_kl | 0.000177 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.00153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 546 |\n", + "| TimestepsSoFar | 7.86e+05 |\n", + "| TimeElapsed | 4.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00527 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 9.68e-11 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.0953 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 546 |\n", + "| TimestepsSoFar | 7.86e+05 |\n", + "| TimeElapsed | 4.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00329 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 0.000414 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.00704 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 546 |\n", + "| TimestepsSoFar | 7.86e+05 |\n", + "| TimeElapsed | 4.18e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000591 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 3.88e-11 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 546 |\n", + "| TimestepsSoFar | 7.86e+05 |\n", + "| TimeElapsed | 4.18e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.362 |\n", + "| loss_vf_loss | 8.49e-11 |\n", + "| loss_kl | 5.8e-05 |\n", + "| loss_ent | 36.2 |\n", + "| ev_tdlam_before | 0.00153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 546 |\n", + "| TimestepsSoFar | 7.86e+05 |\n", + "| TimeElapsed | 4.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00352 |\n", + "| loss_pol_entpen | -0.363 |\n", + "| loss_vf_loss | 3.29e-10 |\n", + "| loss_kl | 0.000352 |\n", + "| loss_ent | 36.3 |\n", + "| ev_tdlam_before | -0.00338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.363 |\n", + "| loss_vf_loss | 3.59e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 36.3 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.2e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00544 |\n", + "| loss_pol_entpen | -0.363 |\n", + "| loss_vf_loss | 2.5e-10 |\n", + "| loss_kl | 0.000496 |\n", + "| loss_ent | 36.3 |\n", + "| ev_tdlam_before | -0.000582 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.2e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.363 |\n", + "| loss_vf_loss | 5.74e-10 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 36.3 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.2e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00174 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 3.33e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | 0.0063 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.363 |\n", + "| loss_vf_loss | 7e-11 |\n", + "| loss_kl | 0.000119 |\n", + "| loss_ent | 36.3 |\n", + "| ev_tdlam_before | 0.0112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 548 |\n", + "| TimestepsSoFar | 7.89e+05 |\n", + "| TimeElapsed | 4.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 1.92e-09 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00483 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 1.36e-09 |\n", + "| loss_kl | 0.000332 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | -0.228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.21e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000844 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | -0.0241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.21e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00424 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 7.67e-10 |\n", + "| loss_kl | 0.000349 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | -0.00709 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.21e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000517 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 2.42e-10 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | 0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.21e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | -0.0328 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 550 |\n", + "| TimestepsSoFar | 7.92e+05 |\n", + "| TimeElapsed | 4.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00286 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 4.8e-11 |\n", + "| loss_kl | 0.000298 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.0214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.000172 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | 0.000193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00222 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 0.000206 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.0484 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0061 |\n", + "| loss_pol_entpen | -0.364 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 0.000416 |\n", + "| loss_ent | 36.4 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000903 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 1.08e-09 |\n", + "| loss_kl | 9.71e-05 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.0692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.23e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 552 |\n", + "| TimestepsSoFar | 7.95e+05 |\n", + "| TimeElapsed | 4.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00357 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 0.000325 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | -0.0341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 554 |\n", + "| TimestepsSoFar | 7.98e+05 |\n", + "| TimeElapsed | 4.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00483 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 0.000462 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.0218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 554 |\n", + "| TimestepsSoFar | 7.98e+05 |\n", + "| TimeElapsed | 4.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 7.17e-10 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.0147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 554 |\n", + "| TimestepsSoFar | 7.98e+05 |\n", + "| TimeElapsed | 4.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000123 |\n", + "| loss_pol_entpen | -0.365 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 8.11e-06 |\n", + "| loss_ent | 36.5 |\n", + "| ev_tdlam_before | -0.00921 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 554 |\n", + "| TimestepsSoFar | 7.98e+05 |\n", + "| TimeElapsed | 4.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0062 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000399 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | 0.00475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 554 |\n", + "| TimestepsSoFar | 7.98e+05 |\n", + "| TimeElapsed | 4.25e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 9.62e-11 |\n", + "| loss_kl | 0.000286 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | 0.000254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 8.76e-05 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | -0.000937 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.26e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 4.63e-11 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | 0.0187 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000206 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | 0.000704 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00457 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.000399 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | -0.00208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.366 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 36.6 |\n", + "| ev_tdlam_before | 0.00308 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 556 |\n", + "| TimestepsSoFar | 8.01e+05 |\n", + "| TimeElapsed | 4.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.00792 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 3.69e-10 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.00582 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 2.61e-10 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00406 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 2.95e-10 |\n", + "| loss_kl | 0.000339 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.00195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.27e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000661 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 5.23e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.00885 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.28e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 5.29e-10 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.0604 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 558 |\n", + "| TimestepsSoFar | 8.04e+05 |\n", + "| TimeElapsed | 4.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.368 |\n", + "| loss_vf_loss | 3.31e-09 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 36.8 |\n", + "| ev_tdlam_before | -0.0919 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.368 |\n", + "| loss_vf_loss | 6.14e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 36.8 |\n", + "| ev_tdlam_before | -0.112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.368 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 36.8 |\n", + "| ev_tdlam_before | -0.034 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.00031 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | -0.0226 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.367 |\n", + "| loss_vf_loss | 6.47e-10 |\n", + "| loss_kl | 7.19e-05 |\n", + "| loss_ent | 36.7 |\n", + "| ev_tdlam_before | 0.000108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.368 |\n", + "| loss_vf_loss | 9.14e-11 |\n", + "| loss_kl | 0.000365 |\n", + "| loss_ent | 36.8 |\n", + "| ev_tdlam_before | -0.00932 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 560 |\n", + "| TimestepsSoFar | 8.06e+05 |\n", + "| TimeElapsed | 4.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00247 |\n", + "| loss_pol_entpen | -0.369 |\n", + "| loss_vf_loss | 6.95e-11 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 36.9 |\n", + "| ev_tdlam_before | -0.0203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 562 |\n", + "| TimestepsSoFar | 8.09e+05 |\n", + "| TimeElapsed | 4.3e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000247 |\n", + "| loss_pol_entpen | -0.369 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 7.53e-05 |\n", + "| loss_ent | 36.9 |\n", + "| ev_tdlam_before | 0.000557 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 562 |\n", + "| TimestepsSoFar | 8.09e+05 |\n", + "| TimeElapsed | 4.3e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00736 |\n", + "| loss_pol_entpen | -0.369 |\n", + "| loss_vf_loss | 1.73e-09 |\n", + "| loss_kl | 0.00043 |\n", + "| loss_ent | 36.9 |\n", + "| ev_tdlam_before | -0.236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 562 |\n", + "| TimestepsSoFar | 8.09e+05 |\n", + "| TimeElapsed | 4.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.369 |\n", + "| loss_vf_loss | 3.97e-10 |\n", + "| loss_kl | 0.0003 |\n", + "| loss_ent | 36.9 |\n", + "| ev_tdlam_before | -0.0633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 562 |\n", + "| TimestepsSoFar | 8.09e+05 |\n", + "| TimeElapsed | 4.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00294 |\n", + "| loss_pol_entpen | -0.369 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 36.9 |\n", + "| ev_tdlam_before | -0.028 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 562 |\n", + "| TimestepsSoFar | 8.09e+05 |\n", + "| TimeElapsed | 4.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00457 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 5.26e-10 |\n", + "| loss_kl | 0.000282 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | -9.97e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00282 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 6.9e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | -0.0481 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 2.42e-10 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | 0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 8.58e-05 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | -0.00194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.00032 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | -0.000943 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00619 |\n", + "| loss_pol_entpen | -0.37 |\n", + "| loss_vf_loss | 1.31e-09 |\n", + "| loss_kl | 0.000538 |\n", + "| loss_ent | 37 |\n", + "| ev_tdlam_before | -0.00147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 564 |\n", + "| TimestepsSoFar | 8.12e+05 |\n", + "| TimeElapsed | 4.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 0.00041 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 0.000147 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.00753 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00499 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 1.4e-09 |\n", + "| loss_kl | 0.000349 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.00125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 4.23e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 7.87e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.0089 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00336 |\n", + "| loss_pol_entpen | -0.371 |\n", + "| loss_vf_loss | 2.31e-10 |\n", + "| loss_kl | 0.000247 |\n", + "| loss_ent | 37.1 |\n", + "| ev_tdlam_before | -0.00735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 566 |\n", + "| TimestepsSoFar | 8.15e+05 |\n", + "| TimeElapsed | 4.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.372 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 0.000176 |\n", + "| loss_ent | 37.2 |\n", + "| ev_tdlam_before | -0.0171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00255 |\n", + "| loss_pol_entpen | -0.372 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 37.2 |\n", + "| ev_tdlam_before | 0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.372 |\n", + "| loss_vf_loss | 8.9e-10 |\n", + "| loss_kl | 9.72e-05 |\n", + "| loss_ent | 37.2 |\n", + "| ev_tdlam_before | -0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.372 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.00016 |\n", + "| loss_ent | 37.2 |\n", + "| ev_tdlam_before | -0.00348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.372 |\n", + "| loss_vf_loss | 2.93e-11 |\n", + "| loss_kl | 0.000177 |\n", + "| loss_ent | 37.2 |\n", + "| ev_tdlam_before | -0.00953 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00694 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 2.6e-10 |\n", + "| loss_kl | 0.000545 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | -7.51e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 568 |\n", + "| TimestepsSoFar | 8.18e+05 |\n", + "| TimeElapsed | 4.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 2.9e-10 |\n", + "| loss_kl | 0.000232 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | -0.0156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 570 |\n", + "| TimestepsSoFar | 8.21e+05 |\n", + "| TimeElapsed | 4.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 5.73e-11 |\n", + "| loss_kl | 0.000158 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 570 |\n", + "| TimestepsSoFar | 8.21e+05 |\n", + "| TimeElapsed | 4.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00457 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000309 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | 0.0045 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 570 |\n", + "| TimestepsSoFar | 8.21e+05 |\n", + "| TimeElapsed | 4.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0052 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 4.01e-11 |\n", + "| loss_kl | 0.000444 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | -0.065 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 570 |\n", + "| TimestepsSoFar | 8.21e+05 |\n", + "| TimeElapsed | 4.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00381 |\n", + "| loss_pol_entpen | -0.373 |\n", + "| loss_vf_loss | 4.16e-11 |\n", + "| loss_kl | 0.000509 |\n", + "| loss_ent | 37.3 |\n", + "| ev_tdlam_before | 0.00557 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 570 |\n", + "| TimestepsSoFar | 8.21e+05 |\n", + "| TimeElapsed | 4.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000554 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 2.84e-10 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.0208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00142 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 5.87e-11 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.00832 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0038 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 7.5e-10 |\n", + "| loss_kl | 0.000249 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.00224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 9.6e-10 |\n", + "| loss_kl | 0.000234 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.0684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.374 |\n", + "| loss_vf_loss | 9.36e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 37.4 |\n", + "| ev_tdlam_before | -0.0231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 572 |\n", + "| TimestepsSoFar | 8.24e+05 |\n", + "| TimeElapsed | 4.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.375 |\n", + "| loss_vf_loss | 3.67e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 37.5 |\n", + "| ev_tdlam_before | -0.0214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.375 |\n", + "| loss_vf_loss | 2.06e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 37.5 |\n", + "| ev_tdlam_before | -0.0275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00309 |\n", + "| loss_pol_entpen | -0.375 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 0.000278 |\n", + "| loss_ent | 37.5 |\n", + "| ev_tdlam_before | -0.00914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00246 |\n", + "| loss_pol_entpen | -0.375 |\n", + "| loss_vf_loss | 4.74e-11 |\n", + "| loss_kl | 0.00022 |\n", + "| loss_ent | 37.5 |\n", + "| ev_tdlam_before | 0.00678 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00482 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 2.96e-10 |\n", + "| loss_kl | 0.000455 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.4e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0023 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 6.57e-11 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | -0.0223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 574 |\n", + "| TimestepsSoFar | 8.27e+05 |\n", + "| TimeElapsed | 4.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00156 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 4.63e-10 |\n", + "| loss_kl | 8.88e-05 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | 0.00349 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.004 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 1.21e-09 |\n", + "| loss_kl | 0.000294 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | -9.2e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | -0.0594 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | 0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.376 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000306 |\n", + "| loss_ent | 37.6 |\n", + "| ev_tdlam_before | 0.00502 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00093 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 8.28e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.0109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 576 |\n", + "| TimestepsSoFar | 8.29e+05 |\n", + "| TimeElapsed | 4.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00261 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 6.05e-10 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 578 |\n", + "| TimestepsSoFar | 8.32e+05 |\n", + "| TimeElapsed | 4.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00298 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000204 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 578 |\n", + "| TimestepsSoFar | 8.32e+05 |\n", + "| TimeElapsed | 4.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00329 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 4.14e-10 |\n", + "| loss_kl | 0.000295 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 578 |\n", + "| TimestepsSoFar | 8.32e+05 |\n", + "| TimeElapsed | 4.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000624 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 7.46e-05 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.0379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 578 |\n", + "| TimestepsSoFar | 8.32e+05 |\n", + "| TimeElapsed | 4.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.377 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 37.7 |\n", + "| ev_tdlam_before | -0.00304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 578 |\n", + "| TimestepsSoFar | 8.32e+05 |\n", + "| TimeElapsed | 4.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 4.95e-10 |\n", + "| loss_kl | 0.000293 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | -0.0155 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 7.18e-11 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | -0.0233 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00142 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 7e-05 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | 0.00412 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 4.25e-11 |\n", + "| loss_kl | 0.000233 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | -0.08 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00214 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 8.23e-11 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | 0.00562 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00184 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 4.49e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | -0.00255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 580 |\n", + "| TimestepsSoFar | 8.35e+05 |\n", + "| TimeElapsed | 4.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00839 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 9.12e-11 |\n", + "| loss_kl | 0.000669 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | -0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.45e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000887 |\n", + "| loss_pol_entpen | -0.378 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 0.000263 |\n", + "| loss_ent | 37.8 |\n", + "| ev_tdlam_before | 0.00581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.45e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00673 |\n", + "| loss_pol_entpen | -0.379 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 0.00042 |\n", + "| loss_ent | 37.9 |\n", + "| ev_tdlam_before | -0.00442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.379 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 0.000367 |\n", + "| loss_ent | 37.9 |\n", + "| ev_tdlam_before | -0.00638 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.379 |\n", + "| loss_vf_loss | 6.5e-11 |\n", + "| loss_kl | 0.000165 |\n", + "| loss_ent | 37.9 |\n", + "| ev_tdlam_before | -0.00366 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00407 |\n", + "| loss_pol_entpen | -0.379 |\n", + "| loss_vf_loss | 2.87e-10 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 37.9 |\n", + "| ev_tdlam_before | -0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 582 |\n", + "| TimestepsSoFar | 8.38e+05 |\n", + "| TimeElapsed | 4.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00404 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 5.48e-10 |\n", + "| loss_kl | 0.000352 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0319 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00342 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 6.84e-10 |\n", + "| loss_kl | 0.000213 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00023 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1e-09 |\n", + "| loss_kl | 2.44e-05 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0603 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 4.28e-10 |\n", + "| loss_kl | 0.000277 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | -0.0249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | 1.66e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 584 |\n", + "| TimestepsSoFar | 8.41e+05 |\n", + "| TimeElapsed | 4.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.379 |\n", + "| loss_vf_loss | 8.96e-11 |\n", + "| loss_kl | 9.89e-05 |\n", + "| loss_ent | 37.9 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 586 |\n", + "| TimestepsSoFar | 8.44e+05 |\n", + "| TimeElapsed | 4.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00471 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 0.000317 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | -0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 586 |\n", + "| TimestepsSoFar | 8.44e+05 |\n", + "| TimeElapsed | 4.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 8.31e-11 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | -0.0136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 586 |\n", + "| TimestepsSoFar | 8.44e+05 |\n", + "| TimeElapsed | 4.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 7.28e-11 |\n", + "| loss_kl | 0.00027 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | -0.00207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 586 |\n", + "| TimestepsSoFar | 8.44e+05 |\n", + "| TimeElapsed | 4.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00368 |\n", + "| loss_pol_entpen | -0.38 |\n", + "| loss_vf_loss | 3.75e-10 |\n", + "| loss_kl | 0.000347 |\n", + "| loss_ent | 38 |\n", + "| ev_tdlam_before | -0.0025 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 586 |\n", + "| TimestepsSoFar | 8.44e+05 |\n", + "| TimeElapsed | 4.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 3.52e-10 |\n", + "| loss_kl | 0.000221 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.0273 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0324 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 0.000127 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.000475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.5e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.000128 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0023 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00239 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 6.06e-11 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.5e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000466 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 2.87e-10 |\n", + "| loss_kl | 8.02e-05 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.000888 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 588 |\n", + "| TimestepsSoFar | 8.47e+05 |\n", + "| TimeElapsed | 4.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00424 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 2.51e-10 |\n", + "| loss_kl | 8.3e-05 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.52e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000358 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 4.2e-05 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.52e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00372 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0394 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 6.78e-11 |\n", + "| loss_kl | 0.000176 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00485 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 5.02e-11 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00369 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 590 |\n", + "| TimestepsSoFar | 8.5e+05 |\n", + "| TimeElapsed | 4.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0517 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00309 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.000577 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.53e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000253 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 9.04e-11 |\n", + "| loss_kl | 7.67e-05 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.53e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00596 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 5.7e-11 |\n", + "| loss_kl | 0.000388 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00667 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00527 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 2.31e-10 |\n", + "| loss_kl | 0.000553 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.000277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 0.000226 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.0199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 592 |\n", + "| TimestepsSoFar | 8.52e+05 |\n", + "| TimeElapsed | 4.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00353 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000286 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | 0.00317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 594 |\n", + "| TimestepsSoFar | 8.55e+05 |\n", + "| TimeElapsed | 4.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 0.000269 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.0207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 594 |\n", + "| TimestepsSoFar | 8.55e+05 |\n", + "| TimeElapsed | 4.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 2.56e-11 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | 0.015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 594 |\n", + "| TimestepsSoFar | 8.55e+05 |\n", + "| TimeElapsed | 4.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00261 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.5e-09 |\n", + "| loss_kl | 0.000199 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | 0.000727 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 594 |\n", + "| TimestepsSoFar | 8.55e+05 |\n", + "| TimeElapsed | 4.55e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 4.35e-09 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.000374 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 594 |\n", + "| TimestepsSoFar | 8.55e+05 |\n", + "| TimeElapsed | 4.55e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.005 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000315 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.0279 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00269 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 3.97e-10 |\n", + "| loss_kl | 0.000337 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.00865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 7.5e-11 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.0336 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.56e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.71e-09 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -2.22e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.56e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.0442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00182 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 0.000127 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | 0.00259 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 596 |\n", + "| TimestepsSoFar | 8.58e+05 |\n", + "| TimeElapsed | 4.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -5.77e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.57e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 4.98e-11 |\n", + "| loss_kl | 0.000176 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.00795 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 4.78e-11 |\n", + "| loss_kl | 0.000249 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | 0.00232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.58e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0035 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 4.7e-11 |\n", + "| loss_kl | 0.000301 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.000923 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.58e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00343 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 8.25e-11 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | 0.000827 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 0.000313 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.00419 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 598 |\n", + "| TimestepsSoFar | 8.61e+05 |\n", + "| TimeElapsed | 4.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 6.2e-11 |\n", + "| loss_kl | 0.000374 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00287 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 7.86e-10 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 6.83e-11 |\n", + "| loss_kl | 0.00031 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00816 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 2.99e-10 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.0294 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 0.000159 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00699 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 8.01e-10 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00886 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 600 |\n", + "| TimestepsSoFar | 8.64e+05 |\n", + "| TimeElapsed | 4.6e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 2.91e-11 |\n", + "| loss_kl | 0.000164 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.0553 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 602 |\n", + "| TimestepsSoFar | 8.67e+05 |\n", + "| TimeElapsed | 4.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.005 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 5.93e-11 |\n", + "| loss_kl | 0.000364 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | 3.09e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 602 |\n", + "| TimestepsSoFar | 8.67e+05 |\n", + "| TimeElapsed | 4.61e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000816 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000159 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.0182 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 602 |\n", + "| TimestepsSoFar | 8.67e+05 |\n", + "| TimeElapsed | 4.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0038 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | 0.0072 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 602 |\n", + "| TimestepsSoFar | 8.67e+05 |\n", + "| TimeElapsed | 4.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.00452 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 602 |\n", + "| TimestepsSoFar | 8.67e+05 |\n", + "| TimeElapsed | 4.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 0.000263 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.0074 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00285 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00463 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 3.19e-11 |\n", + "| loss_kl | 0.000332 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | -0.00398 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.381 |\n", + "| loss_vf_loss | 3.14e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 38.1 |\n", + "| ev_tdlam_before | 0.00142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 4.3e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.0405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00285 |\n", + "| loss_pol_entpen | -0.382 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 38.2 |\n", + "| ev_tdlam_before | -0.031 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 604 |\n", + "| TimestepsSoFar | 8.7e+05 |\n", + "| TimeElapsed | 4.63e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000177 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 7.88e-11 |\n", + "| loss_kl | 5.46e-05 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.00682 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 5.5e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.00282 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 0.000206 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.0327 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 7.33e-10 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 8.5e-10 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.00811 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00351 |\n", + "| loss_pol_entpen | -0.383 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000258 |\n", + "| loss_ent | 38.3 |\n", + "| ev_tdlam_before | -0.00705 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 606 |\n", + "| TimestepsSoFar | 8.73e+05 |\n", + "| TimeElapsed | 4.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000625 |\n", + "| loss_pol_entpen | -0.384 |\n", + "| loss_vf_loss | 5.63e-11 |\n", + "| loss_kl | 9.03e-05 |\n", + "| loss_ent | 38.4 |\n", + "| ev_tdlam_before | 0.000771 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00356 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 8.77e-11 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.65e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00538 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 9.53e-11 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | 0.000154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 1.71e-09 |\n", + "| loss_kl | 0.00012 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | -0.00495 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | -0.055 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 3.5e-10 |\n", + "| loss_kl | 8.06e-05 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | 0.00694 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 608 |\n", + "| TimestepsSoFar | 8.76e+05 |\n", + "| TimeElapsed | 4.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00408 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 0.000383 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 610 |\n", + "| TimestepsSoFar | 8.78e+05 |\n", + "| TimeElapsed | 4.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 2.56e-10 |\n", + "| loss_kl | 0.000362 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | -0.00393 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 610 |\n", + "| TimestepsSoFar | 8.78e+05 |\n", + "| TimeElapsed | 4.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00662 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 7.33e-11 |\n", + "| loss_kl | 0.000495 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | 0.00949 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 610 |\n", + "| TimestepsSoFar | 8.78e+05 |\n", + "| TimeElapsed | 4.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.385 |\n", + "| loss_vf_loss | 4.75e-10 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 38.5 |\n", + "| ev_tdlam_before | 0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 610 |\n", + "| TimestepsSoFar | 8.78e+05 |\n", + "| TimeElapsed | 4.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000236 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.00171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 610 |\n", + "| TimestepsSoFar | 8.78e+05 |\n", + "| TimeElapsed | 4.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 3.2e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 8.02e-11 |\n", + "| loss_kl | 0.000123 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.00781 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000611 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 4.95e-11 |\n", + "| loss_kl | 3.86e-05 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.69e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 2.05e-10 |\n", + "| loss_kl | 9.44e-05 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | 0.00739 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 1.05e-09 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 6.44e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.0879 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 612 |\n", + "| TimestepsSoFar | 8.81e+05 |\n", + "| TimeElapsed | 4.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00557 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 2.39e-09 |\n", + "| loss_kl | 0.00035 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.00834 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000403 |\n", + "| loss_pol_entpen | -0.386 |\n", + "| loss_vf_loss | 6.43e-11 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 38.6 |\n", + "| ev_tdlam_before | -0.169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00453 |\n", + "| loss_pol_entpen | -0.387 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 0.000341 |\n", + "| loss_ent | 38.7 |\n", + "| ev_tdlam_before | 0.000814 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00694 |\n", + "| loss_pol_entpen | -0.387 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 0.000445 |\n", + "| loss_ent | 38.7 |\n", + "| ev_tdlam_before | -0.00348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.387 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 0.000329 |\n", + "| loss_ent | 38.7 |\n", + "| ev_tdlam_before | 0.00621 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.387 |\n", + "| loss_vf_loss | 4.18e-11 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 38.7 |\n", + "| ev_tdlam_before | 0.00129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 614 |\n", + "| TimestepsSoFar | 8.84e+05 |\n", + "| TimeElapsed | 4.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.388 |\n", + "| loss_vf_loss | 2.7e-10 |\n", + "| loss_kl | 6.93e-05 |\n", + "| loss_ent | 38.8 |\n", + "| ev_tdlam_before | -0.00443 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.71e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.388 |\n", + "| loss_vf_loss | 2.59e-10 |\n", + "| loss_kl | 0.000166 |\n", + "| loss_ent | 38.8 |\n", + "| ev_tdlam_before | -9.29e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.71e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00686 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 3.65e-10 |\n", + "| loss_kl | 0.000486 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | 0.000598 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00266 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 2.25e-10 |\n", + "| loss_kl | 0.000356 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.01 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 3.93e-10 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00437 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 9.9e-10 |\n", + "| loss_kl | 0.000367 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.1 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 616 |\n", + "| TimestepsSoFar | 8.87e+05 |\n", + "| TimeElapsed | 4.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00537 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000373 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.072 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 618 |\n", + "| TimestepsSoFar | 8.9e+05 |\n", + "| TimeElapsed | 4.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 2e-10 |\n", + "| loss_kl | 0.000218 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.0364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 618 |\n", + "| TimestepsSoFar | 8.9e+05 |\n", + "| TimeElapsed | 4.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 5.89e-10 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | 0.00633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 618 |\n", + "| TimestepsSoFar | 8.9e+05 |\n", + "| TimeElapsed | 4.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 618 |\n", + "| TimestepsSoFar | 8.9e+05 |\n", + "| TimeElapsed | 4.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 5.85e-10 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | 0.00184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 618 |\n", + "| TimestepsSoFar | 8.9e+05 |\n", + "| TimeElapsed | 4.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00142 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 1.22e-09 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.0397 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00399 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 6.88e-10 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0668 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.75e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000781 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 8.06e-11 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.0002 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.00016 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.000623 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 0.000183 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00799 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 620 |\n", + "| TimestepsSoFar | 8.93e+05 |\n", + "| TimeElapsed | 4.75e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00743 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00304 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | 7.61e-05 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.29e-09 |\n", + "| loss_kl | 7.81e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.000566 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.76e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.47e-09 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0016 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 7.98e-09 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0666 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 3.26e-09 |\n", + "| loss_kl | 8.53e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.64 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 622 |\n", + "| TimestepsSoFar | 8.96e+05 |\n", + "| TimeElapsed | 4.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00229 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 5.27e-11 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00783 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 2.88e-10 |\n", + "| loss_kl | 6.57e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.000118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00367 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000279 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00485 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000359 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.82e-10 |\n", + "| loss_kl | 0.000345 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 7.46e-10 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 624 |\n", + "| TimestepsSoFar | 8.99e+05 |\n", + "| TimeElapsed | 4.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.389 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 6.35e-05 |\n", + "| loss_ent | 38.9 |\n", + "| ev_tdlam_before | -0.0154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 626 |\n", + "| TimestepsSoFar | 9.01e+05 |\n", + "| TimeElapsed | 4.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00402 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 0.000288 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 626 |\n", + "| TimestepsSoFar | 9.01e+05 |\n", + "| TimeElapsed | 4.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.48e-10 |\n", + "| loss_kl | 0.0004 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.000829 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 626 |\n", + "| TimestepsSoFar | 9.01e+05 |\n", + "| TimeElapsed | 4.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 6.26e-10 |\n", + "| loss_kl | 0.000245 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00446 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 626 |\n", + "| TimestepsSoFar | 9.01e+05 |\n", + "| TimeElapsed | 4.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00409 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0261 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 626 |\n", + "| TimestepsSoFar | 9.01e+05 |\n", + "| TimeElapsed | 4.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00379 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 6.22e-11 |\n", + "| loss_kl | 0.000253 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00815 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.005 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.24e-11 |\n", + "| loss_kl | 0.000272 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.81e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00228 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 5.87e-11 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 3.23e-10 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.000543 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 9.25e-10 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.000651 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000834 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.16e-10 |\n", + "| loss_kl | 5.07e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 628 |\n", + "| TimestepsSoFar | 9.04e+05 |\n", + "| TimeElapsed | 4.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 8.89e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00224 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 9.32e-11 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.000793 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.82e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00452 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | 0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 4.74e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0411 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 7.81e-11 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0453 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000849 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 4.68e-11 |\n", + "| loss_kl | 8.56e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00856 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 630 |\n", + "| TimestepsSoFar | 9.07e+05 |\n", + "| TimeElapsed | 4.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00376 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 6.72e-10 |\n", + "| loss_kl | 0.000289 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 7.53e-10 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0329 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 4.44e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00738 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.88e-09 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0742 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 7.23e-10 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0892 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 632 |\n", + "| TimestepsSoFar | 9.1e+05 |\n", + "| TimeElapsed | 4.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 7.81e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 634 |\n", + "| TimestepsSoFar | 9.13e+05 |\n", + "| TimeElapsed | 4.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 3.46e-11 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0315 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 634 |\n", + "| TimestepsSoFar | 9.13e+05 |\n", + "| TimeElapsed | 4.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000875 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.66e-11 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 634 |\n", + "| TimestepsSoFar | 9.13e+05 |\n", + "| TimeElapsed | 4.85e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000942 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 8.51e-11 |\n", + "| loss_kl | 6.23e-05 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.02 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 634 |\n", + "| TimestepsSoFar | 9.13e+05 |\n", + "| TimeElapsed | 4.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00526 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 634 |\n", + "| TimestepsSoFar | 9.13e+05 |\n", + "| TimeElapsed | 4.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 4.95e-11 |\n", + "| loss_kl | 0.000146 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00197 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 0.000158 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00608 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00181 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.31e-09 |\n", + "| loss_kl | 0.000178 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00963 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.03e-09 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0287 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 2.71e-09 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.000263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 636 |\n", + "| TimestepsSoFar | 9.16e+05 |\n", + "| TimeElapsed | 4.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00436 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000275 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 8.95e-10 |\n", + "| loss_kl | 0.000238 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.00553 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 9.69e-11 |\n", + "| loss_kl | 0.00026 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0293 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 8.42e-11 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.00129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 5.21e-11 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | 0.000306 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.39 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 39 |\n", + "| ev_tdlam_before | -0.0392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 638 |\n", + "| TimestepsSoFar | 9.19e+05 |\n", + "| TimeElapsed | 4.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00584 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 2.73e-10 |\n", + "| loss_kl | 0.000422 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | 0.000295 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | 0.000942 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000787 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 4.19e-10 |\n", + "| loss_kl | 2.78e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00979 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000649 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 6.14e-10 |\n", + "| loss_kl | 5.05e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 2.39e-09 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0267 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 7.66e-11 |\n", + "| loss_kl | 9.82e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0744 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 640 |\n", + "| TimestepsSoFar | 9.22e+05 |\n", + "| TimeElapsed | 4.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 1.9e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0445 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 642 |\n", + "| TimestepsSoFar | 9.24e+05 |\n", + "| TimeElapsed | 4.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00309 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 0.000217 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 642 |\n", + "| TimestepsSoFar | 9.24e+05 |\n", + "| TimeElapsed | 4.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000786 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 5.27e-11 |\n", + "| loss_kl | 5.24e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0523 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 642 |\n", + "| TimestepsSoFar | 9.24e+05 |\n", + "| TimeElapsed | 4.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 5.64e-10 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.000305 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 642 |\n", + "| TimestepsSoFar | 9.24e+05 |\n", + "| TimeElapsed | 4.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000659 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 6.91e-10 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00997 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 642 |\n", + "| TimestepsSoFar | 9.24e+05 |\n", + "| TimeElapsed | 4.92e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 9.88e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00388 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 6.82e-10 |\n", + "| loss_kl | 0.000319 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00669 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 6.09e-10 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | 0.000133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00248 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.00447 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | 0.00163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000686 |\n", + "| loss_pol_entpen | -0.391 |\n", + "| loss_vf_loss | 4.99e-10 |\n", + "| loss_kl | 9.27e-05 |\n", + "| loss_ent | 39.1 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 644 |\n", + "| TimestepsSoFar | 9.27e+05 |\n", + "| TimeElapsed | 4.93e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 4.74e-10 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | 0.00102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 1.74e-10 |\n", + "| loss_kl | 0.000307 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.12 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000792 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.0055 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00301 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 0.000191 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.0335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00266 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 8.73e-11 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | 0.00295 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00347 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 2.99e-10 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | -0.00324 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 646 |\n", + "| TimestepsSoFar | 9.3e+05 |\n", + "| TimeElapsed | 4.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 4.46e-10 |\n", + "| loss_kl | 0.000221 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 2.88e-10 |\n", + "| loss_kl | 0.00024 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00496 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 3.05e-10 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.00346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.000294 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.00626 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00472 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 4.85e-10 |\n", + "| loss_kl | 0.000404 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00312 |\n", + "| loss_pol_entpen | -0.392 |\n", + "| loss_vf_loss | 5.29e-11 |\n", + "| loss_kl | 0.000325 |\n", + "| loss_ent | 39.2 |\n", + "| ev_tdlam_before | -0.0132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 648 |\n", + "| TimestepsSoFar | 9.33e+05 |\n", + "| TimeElapsed | 4.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 0.000176 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | 0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 650 |\n", + "| TimestepsSoFar | 9.36e+05 |\n", + "| TimeElapsed | 4.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | 0.000655 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 650 |\n", + "| TimestepsSoFar | 9.36e+05 |\n", + "| TimeElapsed | 4.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 8.29e-05 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | -0.0393 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 650 |\n", + "| TimestepsSoFar | 9.36e+05 |\n", + "| TimeElapsed | 4.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 4.81e-10 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | -0.00423 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 650 |\n", + "| TimestepsSoFar | 9.36e+05 |\n", + "| TimeElapsed | 4.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00497 |\n", + "| loss_pol_entpen | -0.393 |\n", + "| loss_vf_loss | 1.86e-10 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 39.3 |\n", + "| ev_tdlam_before | 0.00205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 650 |\n", + "| TimestepsSoFar | 9.36e+05 |\n", + "| TimeElapsed | 4.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | 0.0152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 4.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00526 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 0.000303 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | 0.00173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 4.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00656 |\n", + "| loss_pol_entpen | -0.394 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 0.000572 |\n", + "| loss_ent | 39.4 |\n", + "| ev_tdlam_before | -0.00425 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 4.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.394 |\n", + "| loss_vf_loss | 6.46e-11 |\n", + "| loss_kl | 0.00026 |\n", + "| loss_ent | 39.4 |\n", + "| ev_tdlam_before | -0.0017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 4.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.394 |\n", + "| loss_vf_loss | 4.11e-10 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 39.4 |\n", + "| ev_tdlam_before | -0.00438 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 4.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.394 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 39.4 |\n", + "| ev_tdlam_before | -0.023 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 652 |\n", + "| TimestepsSoFar | 9.39e+05 |\n", + "| TimeElapsed | 5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0026 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.00962 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00373 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.00026 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.00804 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5.01e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000701 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.00709 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5.01e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00356 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 7.94e-10 |\n", + "| loss_kl | 0.000221 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.00305 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.0235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | 0.00357 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 654 |\n", + "| TimestepsSoFar | 9.42e+05 |\n", + "| TimeElapsed | 5.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | 0.00181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 3.72e-11 |\n", + "| loss_kl | 0.000197 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | -0.00177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00362 |\n", + "| loss_pol_entpen | -0.395 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.00031 |\n", + "| loss_ent | 39.5 |\n", + "| ev_tdlam_before | 0.0017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00479 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 0.000429 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -0.0113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00303 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 9.42e-11 |\n", + "| loss_kl | 0.000374 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -0.0211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0024 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 5.51e-11 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | 0.000388 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 656 |\n", + "| TimestepsSoFar | 9.45e+05 |\n", + "| TimeElapsed | 5.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00215 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 3.69e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.00314 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 658 |\n", + "| TimestepsSoFar | 9.48e+05 |\n", + "| TimeElapsed | 5.04e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000774 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 7.26e-10 |\n", + "| loss_kl | 9.72e-05 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.00963 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 658 |\n", + "| TimestepsSoFar | 9.48e+05 |\n", + "| TimeElapsed | 5.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 9.44e-10 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.000187 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 658 |\n", + "| TimestepsSoFar | 9.48e+05 |\n", + "| TimeElapsed | 5.04e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 5.91e-10 |\n", + "| loss_kl | 5.61e-05 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.11 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 658 |\n", + "| TimestepsSoFar | 9.48e+05 |\n", + "| TimeElapsed | 5.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 658 |\n", + "| TimestepsSoFar | 9.48e+05 |\n", + "| TimeElapsed | 5.04e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 2.91e-10 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -7.45e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 7.97e-11 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | 0.000302 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000139 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -0.0036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 0.000269 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -0.00345 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 6.48e-11 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | 0.00539 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.06e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.396 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 8.26e-05 |\n", + "| loss_ent | 39.6 |\n", + "| ev_tdlam_before | -0.000564 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 660 |\n", + "| TimestepsSoFar | 9.5e+05 |\n", + "| TimeElapsed | 5.06e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 0.000195 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | 0.00128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 0.000159 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.0411 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000898 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 9.07e-11 |\n", + "| loss_kl | 9.81e-05 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00251 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 2.28e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 4.49e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.00655 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 6.71e-10 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 662 |\n", + "| TimestepsSoFar | 9.53e+05 |\n", + "| TimeElapsed | 5.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 3.02e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00345 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 5.62e-11 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.049 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 6.02e-11 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | 0.00925 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000885 |\n", + "| loss_pol_entpen | -0.397 |\n", + "| loss_vf_loss | 4.68e-11 |\n", + "| loss_kl | 8.37e-05 |\n", + "| loss_ent | 39.7 |\n", + "| ev_tdlam_before | -0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.398 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 39.8 |\n", + "| ev_tdlam_before | -0.00243 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00389 |\n", + "| loss_pol_entpen | -0.398 |\n", + "| loss_vf_loss | 2e-10 |\n", + "| loss_kl | 0.000316 |\n", + "| loss_ent | 39.8 |\n", + "| ev_tdlam_before | 0.000715 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 664 |\n", + "| TimestepsSoFar | 9.56e+05 |\n", + "| TimeElapsed | 5.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.399 |\n", + "| loss_vf_loss | 7.24e-10 |\n", + "| loss_kl | 0.000356 |\n", + "| loss_ent | 39.9 |\n", + "| ev_tdlam_before | 0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 666 |\n", + "| TimestepsSoFar | 9.59e+05 |\n", + "| TimeElapsed | 5.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 7.79e-10 |\n", + "| loss_kl | 0.000224 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.034 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 666 |\n", + "| TimestepsSoFar | 9.59e+05 |\n", + "| TimeElapsed | 5.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.0331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 666 |\n", + "| TimestepsSoFar | 9.59e+05 |\n", + "| TimeElapsed | 5.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 2.67e-10 |\n", + "| loss_kl | 0.000138 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 666 |\n", + "| TimestepsSoFar | 9.59e+05 |\n", + "| TimeElapsed | 5.1e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000557 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 3.3e-10 |\n", + "| loss_kl | 6.36e-05 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 666 |\n", + "| TimestepsSoFar | 9.59e+05 |\n", + "| TimeElapsed | 5.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000281 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | 0.0004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.11e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 0.000192 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.0153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00218 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 3.22e-09 |\n", + "| loss_kl | 0.000188 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.00385 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 4.49e-10 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000511 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 5.75e-11 |\n", + "| loss_kl | 9.19e-05 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | 0.00353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.4 |\n", + "| loss_vf_loss | 1.94e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 40 |\n", + "| ev_tdlam_before | -0.0176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 668 |\n", + "| TimestepsSoFar | 9.62e+05 |\n", + "| TimeElapsed | 5.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.402 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 0.000327 |\n", + "| loss_ent | 40.2 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00223 |\n", + "| loss_pol_entpen | -0.402 |\n", + "| loss_vf_loss | 2.88e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 40.2 |\n", + "| ev_tdlam_before | -0.00776 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.402 |\n", + "| loss_vf_loss | 4.59e-10 |\n", + "| loss_kl | 0.000159 |\n", + "| loss_ent | 40.2 |\n", + "| ev_tdlam_before | -0.0158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00284 |\n", + "| loss_pol_entpen | -0.402 |\n", + "| loss_vf_loss | 9.39e-11 |\n", + "| loss_kl | 0.000252 |\n", + "| loss_ent | 40.2 |\n", + "| ev_tdlam_before | -0.0947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.402 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 40.2 |\n", + "| ev_tdlam_before | -0.00662 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00394 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 670 |\n", + "| TimestepsSoFar | 9.65e+05 |\n", + "| TimeElapsed | 5.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000936 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 3.37e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | -0.00791 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0031 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 3.94e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | -0.00702 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 5.5e-11 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | -0.0965 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00377 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 0.000346 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | 0.000827 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.403 |\n", + "| loss_vf_loss | 3e-10 |\n", + "| loss_kl | 0.000215 |\n", + "| loss_ent | 40.3 |\n", + "| ev_tdlam_before | 0.00806 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 672 |\n", + "| TimestepsSoFar | 9.68e+05 |\n", + "| TimeElapsed | 5.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 674 |\n", + "| TimestepsSoFar | 9.71e+05 |\n", + "| TimeElapsed | 5.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 4.13e-10 |\n", + "| loss_kl | 8.37e-05 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.00467 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 674 |\n", + "| TimestepsSoFar | 9.71e+05 |\n", + "| TimeElapsed | 5.16e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 3.75e-10 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.00061 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 674 |\n", + "| TimestepsSoFar | 9.71e+05 |\n", + "| TimeElapsed | 5.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000166 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 674 |\n", + "| TimestepsSoFar | 9.71e+05 |\n", + "| TimeElapsed | 5.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 9.88e-10 |\n", + "| loss_kl | 0.000179 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.00417 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 674 |\n", + "| TimestepsSoFar | 9.71e+05 |\n", + "| TimeElapsed | 5.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 4.19e-09 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00278 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 1.64e-09 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0967 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 1.18e-09 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 2.84e-10 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 0.000148 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0756 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00246 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 1.13e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 676 |\n", + "| TimestepsSoFar | 9.73e+05 |\n", + "| TimeElapsed | 5.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 2.44e-10 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.000346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000516 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 4.29e-11 |\n", + "| loss_kl | 6.18e-05 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -0.0368 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00197 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 2.67e-10 |\n", + "| loss_kl | 0.000123 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | -3.11e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 6.91e-11 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.00588 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00329 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 3.05e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.00148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00686 |\n", + "| loss_pol_entpen | -0.404 |\n", + "| loss_vf_loss | 5.1e-11 |\n", + "| loss_kl | 0.000567 |\n", + "| loss_ent | 40.4 |\n", + "| ev_tdlam_before | 0.00349 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 678 |\n", + "| TimestepsSoFar | 9.76e+05 |\n", + "| TimeElapsed | 5.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 6.01e-05 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | -0.00304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.2e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.002 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 3.09e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | -0.000949 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.2e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 1.68e-09 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | 0.000335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 3.41e-10 |\n", + "| loss_kl | 7.3e-05 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | -0.0683 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.21e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 7.18e-05 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | 0.00861 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00228 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 1.15e-09 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | -0.00985 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 680 |\n", + "| TimestepsSoFar | 9.79e+05 |\n", + "| TimeElapsed | 5.21e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000551 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 3.96e-10 |\n", + "| loss_kl | 3.21e-05 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | 0.000991 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 682 |\n", + "| TimestepsSoFar | 9.82e+05 |\n", + "| TimeElapsed | 5.22e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000564 |\n", + "| loss_pol_entpen | -0.405 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 3.74e-05 |\n", + "| loss_ent | 40.5 |\n", + "| ev_tdlam_before | -0.00659 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 682 |\n", + "| TimestepsSoFar | 9.82e+05 |\n", + "| TimeElapsed | 5.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.406 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.000237 |\n", + "| loss_ent | 40.6 |\n", + "| ev_tdlam_before | -0.0082 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 682 |\n", + "| TimestepsSoFar | 9.82e+05 |\n", + "| TimeElapsed | 5.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.406 |\n", + "| loss_vf_loss | 4.56e-11 |\n", + "| loss_kl | 0.000331 |\n", + "| loss_ent | 40.6 |\n", + "| ev_tdlam_before | -0.0032 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 682 |\n", + "| TimestepsSoFar | 9.82e+05 |\n", + "| TimeElapsed | 5.22e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.406 |\n", + "| loss_vf_loss | 4.68e-10 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 40.6 |\n", + "| ev_tdlam_before | -2.65e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 682 |\n", + "| TimestepsSoFar | 9.82e+05 |\n", + "| TimeElapsed | 5.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.407 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000168 |\n", + "| loss_ent | 40.7 |\n", + "| ev_tdlam_before | -0.0576 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000576 |\n", + "| loss_pol_entpen | -0.407 |\n", + "| loss_vf_loss | 1.47e-09 |\n", + "| loss_kl | 6.93e-05 |\n", + "| loss_ent | 40.7 |\n", + "| ev_tdlam_before | 0.00125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.23e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00314 |\n", + "| loss_pol_entpen | -0.407 |\n", + "| loss_vf_loss | 3.74e-11 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 40.7 |\n", + "| ev_tdlam_before | -0.179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.408 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 0.000372 |\n", + "| loss_ent | 40.8 |\n", + "| ev_tdlam_before | -0.00201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.408 |\n", + "| loss_vf_loss | 3.31e-10 |\n", + "| loss_kl | 0.000148 |\n", + "| loss_ent | 40.8 |\n", + "| ev_tdlam_before | -0.00998 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00465 |\n", + "| loss_pol_entpen | -0.408 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 0.000373 |\n", + "| loss_ent | 40.8 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 684 |\n", + "| TimestepsSoFar | 9.85e+05 |\n", + "| TimeElapsed | 5.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | -0.00611 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | 0.000444 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000554 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 5.64e-10 |\n", + "| loss_kl | 3.09e-05 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | 0.000586 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000511 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 6.74e-11 |\n", + "| loss_kl | 3.03e-05 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | -0.0395 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0005 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 3.25e-05 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | 0.000123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00181 |\n", + "| loss_pol_entpen | -0.409 |\n", + "| loss_vf_loss | 4.92e-11 |\n", + "| loss_kl | 7.68e-05 |\n", + "| loss_ent | 40.9 |\n", + "| ev_tdlam_before | 0.00987 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 686 |\n", + "| TimestepsSoFar | 9.88e+05 |\n", + "| TimeElapsed | 5.26e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00662 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 4.6e-10 |\n", + "| loss_kl | 0.000466 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | 0.000454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00859 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 0.0006 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.00148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.00034 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.00354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 2.53e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | 0.0016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.27e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000889 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 4.95e-05 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.00792 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.27e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 1.01e-09 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.0131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 688 |\n", + "| TimestepsSoFar | 9.91e+05 |\n", + "| TimeElapsed | 5.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 4.27e-11 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.0504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 690 |\n", + "| TimestepsSoFar | 9.94e+05 |\n", + "| TimeElapsed | 5.28e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.000503 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 690 |\n", + "| TimestepsSoFar | 9.94e+05 |\n", + "| TimeElapsed | 5.28e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.41 |\n", + "| loss_vf_loss | 2.13e-10 |\n", + "| loss_kl | 6.71e-05 |\n", + "| loss_ent | 41 |\n", + "| ev_tdlam_before | -0.00474 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 690 |\n", + "| TimestepsSoFar | 9.94e+05 |\n", + "| TimeElapsed | 5.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00307 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.000255 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 690 |\n", + "| TimestepsSoFar | 9.94e+05 |\n", + "| TimeElapsed | 5.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00312 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 4.33e-10 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | -0.00167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 690 |\n", + "| TimestepsSoFar | 9.94e+05 |\n", + "| TimeElapsed | 5.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00421 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 8.99e-10 |\n", + "| loss_kl | 0.00021 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | -0.00426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | 0.00204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0067 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 8.54e-11 |\n", + "| loss_kl | 0.000447 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | 0.000661 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.3e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000446 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 8.52e-11 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | -0.00385 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.3e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | 0.00193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 7.15e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | 0.00191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 692 |\n", + "| TimestepsSoFar | 9.96e+05 |\n", + "| TimeElapsed | 5.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.411 |\n", + "| loss_vf_loss | 3.52e-10 |\n", + "| loss_kl | 0.000172 |\n", + "| loss_ent | 41.1 |\n", + "| ev_tdlam_before | -0.0022 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0046 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 7.3e-11 |\n", + "| loss_kl | 0.000357 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.0742 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.31e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | 5.39e-05 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 7.59e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000987 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 9.21e-11 |\n", + "| loss_kl | 4.77e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.31e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 6.41e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.83e-10 |\n", + "| loss_kl | 8.39e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.0343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 694 |\n", + "| TimestepsSoFar | 9.99e+05 |\n", + "| TimeElapsed | 5.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0016 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.06e-09 |\n", + "| loss_kl | 9.29e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.0205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 9.48e-11 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 3.31e-11 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00785 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00353 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 4.64e-11 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 6.39e-10 |\n", + "| loss_kl | 0.00018 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00407 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00341 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 6.35e-10 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 696 |\n", + "| TimestepsSoFar | 1e+06 |\n", + "| TimeElapsed | 5.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 6.91e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.000228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 698 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.34e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000704 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 3.59e-10 |\n", + "| loss_kl | 7e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | 0.00362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 698 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.34e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00378 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000251 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.025 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 698 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.00011 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 5.46e-10 |\n", + "| loss_kl | 1.68e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 698 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000717 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 6.66e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | 0.00361 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 698 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | 0.00184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 3.53e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00649 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000246 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.54e-10 |\n", + "| loss_kl | 2.58e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 5.39e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | -0.00618 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000997 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 2.05e-10 |\n", + "| loss_kl | 6.39e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | 1.01e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 700 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.412 |\n", + "| loss_vf_loss | 1.91e-09 |\n", + "| loss_kl | 8.95e-05 |\n", + "| loss_ent | 41.2 |\n", + "| ev_tdlam_before | 0.000675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0035 |\n", + "| loss_pol_entpen | -0.413 |\n", + "| loss_vf_loss | 6.53e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 41.3 |\n", + "| ev_tdlam_before | -0.0313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00363 |\n", + "| loss_pol_entpen | -0.413 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000244 |\n", + "| loss_ent | 41.3 |\n", + "| ev_tdlam_before | -0.0758 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.413 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 0.000317 |\n", + "| loss_ent | 41.3 |\n", + "| ev_tdlam_before | -0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.413 |\n", + "| loss_vf_loss | 7.39e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 41.3 |\n", + "| ev_tdlam_before | 0.00173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00255 |\n", + "| loss_pol_entpen | -0.413 |\n", + "| loss_vf_loss | 3.44e-11 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 41.3 |\n", + "| ev_tdlam_before | -0.0624 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 702 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.415 |\n", + "| loss_vf_loss | 2.97e-10 |\n", + "| loss_kl | 0.000261 |\n", + "| loss_ent | 41.5 |\n", + "| ev_tdlam_before | -0.00024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.415 |\n", + "| loss_vf_loss | 7.48e-11 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 41.5 |\n", + "| ev_tdlam_before | -0.0172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.415 |\n", + "| loss_vf_loss | 2.82e-11 |\n", + "| loss_kl | 0.000297 |\n", + "| loss_ent | 41.5 |\n", + "| ev_tdlam_before | -0.000647 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00602 |\n", + "| loss_pol_entpen | -0.414 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000362 |\n", + "| loss_ent | 41.4 |\n", + "| ev_tdlam_before | -0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.09e-05 |\n", + "| loss_pol_entpen | -0.414 |\n", + "| loss_vf_loss | 4.08e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 41.4 |\n", + "| ev_tdlam_before | -0.0342 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00448 |\n", + "| loss_pol_entpen | -0.414 |\n", + "| loss_vf_loss | 7.4e-11 |\n", + "| loss_kl | 0.00021 |\n", + "| loss_ent | 41.4 |\n", + "| ev_tdlam_before | -0.0866 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 704 |\n", + "| TimestepsSoFar | 1.01e+06 |\n", + "| TimeElapsed | 5.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000759 |\n", + "| loss_pol_entpen | -0.415 |\n", + "| loss_vf_loss | 1.34e-09 |\n", + "| loss_kl | 5.92e-05 |\n", + "| loss_ent | 41.5 |\n", + "| ev_tdlam_before | 0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 706 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00295 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.000204 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | -0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 706 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.000139 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | -0.00929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 706 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00043 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | 0.00269 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 706 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 0.00016 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | 0.0062 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 706 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.41e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 4.75e-11 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | 0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00152 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.000953 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000243 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.022 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00332 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 3.09e-10 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00491 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 5.77e-10 |\n", + "| loss_kl | 0.000387 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00899 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00511 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 5.74e-10 |\n", + "| loss_kl | 0.000436 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0421 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 708 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 3.44e-10 |\n", + "| loss_kl | 4.71e-05 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | -0.00339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000665 |\n", + "| loss_pol_entpen | -0.416 |\n", + "| loss_vf_loss | 8.99e-11 |\n", + "| loss_kl | 3.5e-05 |\n", + "| loss_ent | 41.6 |\n", + "| ev_tdlam_before | -0.0199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 3.49e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00522 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000273 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00556 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 8.5e-11 |\n", + "| loss_kl | 0.000218 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | 0.00032 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000264 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 710 |\n", + "| TimestepsSoFar | 1.02e+06 |\n", + "| TimeElapsed | 5.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 2.92e-11 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00551 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 9.03e-11 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0044 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 3.09e-10 |\n", + "| loss_kl | 7.89e-05 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000341 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 3.36e-05 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0724 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000946 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 5.17e-05 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00911 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 7.86e-11 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | 0.000426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000251 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 712 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 714 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.46e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00224 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 3.92e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.00475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 714 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.46e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.417 |\n", + "| loss_vf_loss | 5.99e-10 |\n", + "| loss_kl | 8.67e-05 |\n", + "| loss_ent | 41.7 |\n", + "| ev_tdlam_before | -0.0439 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 714 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00339 |\n", + "| loss_pol_entpen | -0.418 |\n", + "| loss_vf_loss | 2.13e-10 |\n", + "| loss_kl | 0.000233 |\n", + "| loss_ent | 41.8 |\n", + "| ev_tdlam_before | -0.0154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 714 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00186 |\n", + "| loss_pol_entpen | -0.418 |\n", + "| loss_vf_loss | 8.58e-10 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 41.8 |\n", + "| ev_tdlam_before | -0.00238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 714 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00182 |\n", + "| loss_pol_entpen | -0.418 |\n", + "| loss_vf_loss | 9e-11 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 41.8 |\n", + "| ev_tdlam_before | -0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.418 |\n", + "| loss_vf_loss | 2.47e-10 |\n", + "| loss_kl | 4.12e-05 |\n", + "| loss_ent | 41.8 |\n", + "| ev_tdlam_before | -0.00115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00282 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 0.000138 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.00562 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000353 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 6.7e-11 |\n", + "| loss_kl | 8.83e-05 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0818 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 3.58e-10 |\n", + "| loss_kl | 7.33e-05 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | 0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 716 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 5.95e-11 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0646 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00468 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 3.06e-10 |\n", + "| loss_kl | 0.000235 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00413 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.54e-11 |\n", + "| loss_kl | 0.000311 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00296 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.13e-10 |\n", + "| loss_kl | 0.000178 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00097 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00528 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.00032 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 718 |\n", + "| TimestepsSoFar | 1.03e+06 |\n", + "| TimeElapsed | 5.5e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00717 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 4.96e-09 |\n", + "| loss_kl | 0.00046 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -2.49e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 3.35e-09 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 6.52e-10 |\n", + "| loss_kl | 9.11e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.221 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00218 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 4.45e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000614 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 5.07e-10 |\n", + "| loss_kl | 2.15e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.0255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 9.37e-10 |\n", + "| loss_kl | 7.63e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000265 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 720 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 9.16e-11 |\n", + "| loss_kl | 0.00029 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 722 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.33e-10 |\n", + "| loss_kl | 0.000202 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 722 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.53e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000856 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 6.84e-10 |\n", + "| loss_kl | 5.07e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 722 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.53e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.93e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 722 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 3.4e-10 |\n", + "| loss_kl | 0.000189 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 722 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.53e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 7.71e-11 |\n", + "| loss_kl | 9.94e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.000206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | 0.0134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 3.68e-11 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.21e-06 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 9.54e-11 |\n", + "| loss_kl | 2.84e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00094 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00229 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.00922 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 6.27e-10 |\n", + "| loss_kl | 0.000219 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 724 |\n", + "| TimestepsSoFar | 1.04e+06 |\n", + "| TimeElapsed | 5.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00076 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.83e-10 |\n", + "| loss_kl | 3.14e-05 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000164 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.56e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000886 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 6.93e-11 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.00365 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.56e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00556 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 0.000314 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.000352 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.56e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 2.98e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.56e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.419 |\n", + "| loss_vf_loss | 3.62e-10 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 41.9 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 726 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00059 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 4.86e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.000192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.31e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00243 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 4.29e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000732 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.25e-09 |\n", + "| loss_kl | 7.15e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00288 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.57e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00348 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0625 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 728 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.35e-10 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.000369 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 730 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 730 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.8e-10 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 730 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.59e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000548 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 7.05e-11 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 730 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000495 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 4.08e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 730 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000953 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 6.13e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 2.46e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 9.64e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00156 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 6.11e-10 |\n", + "| loss_kl | 9.25e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0508 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00616 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 7.56e-11 |\n", + "| loss_kl | 0.000465 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0654 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 732 |\n", + "| TimestepsSoFar | 1.05e+06 |\n", + "| TimeElapsed | 5.61e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000303 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 5.56e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.00229 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 7.64e-05 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 5.57e-11 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | -0.0392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.42 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 42 |\n", + "| ev_tdlam_before | 0.000258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 6.17e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.000266 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00287 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 3.48e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.0448 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 734 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.62e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.37e-09 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.000562 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.63e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.0429 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.63e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000958 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | 4.01e-05 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | 0.000521 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.63e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 9.41e-05 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | 0.00392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 736 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 7.87e-11 |\n", + "| loss_kl | 0.000328 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | 0.000503 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 738 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | -0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 738 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.65e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000702 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 5.61e-05 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | -0.0107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 738 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.65e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0026 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | -0.000635 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 738 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00219 |\n", + "| loss_pol_entpen | -0.421 |\n", + "| loss_vf_loss | 7.01e-10 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 42.1 |\n", + "| ev_tdlam_before | 0.000276 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000254 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 738 |\n", + "| TimestepsSoFar | 1.06e+06 |\n", + "| TimeElapsed | 5.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 6e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | -0.00657 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 4.56e-10 |\n", + "| loss_kl | 0.000228 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | -0.0528 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.422 |\n", + "| loss_vf_loss | 2.41e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 42.2 |\n", + "| ev_tdlam_before | -0.0055 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.66e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 5e-10 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00391 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 3.88e-10 |\n", + "| loss_kl | 0.000259 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 0.000274 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.00507 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 740 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.67e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 4.29e-10 |\n", + "| loss_kl | 7.32e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.000229 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 2.8e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00424 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 0.000182 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00685 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000756 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 3.23e-09 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.000376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 4.89e-10 |\n", + "| loss_kl | 9.79e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 4.19e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0084 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000255 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 742 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00289 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.00544 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.69e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000753 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 3.83e-10 |\n", + "| loss_kl | 5.71e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.000608 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.69e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 6.95e-11 |\n", + "| loss_kl | 0.000155 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.03 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.69e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000922 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 6.59e-11 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 8.84e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 4.49e-11 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0451 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 744 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.7e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000595 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 4.67e-10 |\n", + "| loss_kl | 6.6e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.00247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 746 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000748 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 8.65e-11 |\n", + "| loss_kl | 6.01e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 746 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000861 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 7.28e-11 |\n", + "| loss_kl | 3.6e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.000154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 746 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.71e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 7.18e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00871 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 746 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.71e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00472 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 3.96e-10 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 746 |\n", + "| TimestepsSoFar | 1.07e+06 |\n", + "| TimeElapsed | 5.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 8.98e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.000214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 9.34e-10 |\n", + "| loss_kl | 9.45e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00142 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 2.49e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.02 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00196 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 2.38e-10 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.000211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00377 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 3e-10 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 748 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.83e-09 |\n", + "| loss_kl | 5.81e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0274 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000164 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 6.74e-10 |\n", + "| loss_kl | 2.89e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 3.74e-10 |\n", + "| loss_kl | 5.73e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00438 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 3.64e-10 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 0.000261 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | -0.0678 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.423 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 7.84e-05 |\n", + "| loss_ent | 42.3 |\n", + "| ev_tdlam_before | 0.00236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 750 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 4.7e-10 |\n", + "| loss_kl | 0.000147 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0952 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.75e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000169 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 5.16e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0797 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00736 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 3.27e-10 |\n", + "| loss_kl | 0.000375 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00555 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0032 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 5.56e-10 |\n", + "| loss_kl | 0.000397 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00214 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 5.31e-10 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00326 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 4.21e-10 |\n", + "| loss_kl | 0.000202 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.00422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 752 |\n", + "| TimestepsSoFar | 1.08e+06 |\n", + "| TimeElapsed | 5.76e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 5.7e-11 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 754 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 5.84e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 754 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 4.7e-11 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 754 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 0.000139 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 754 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 3.85e-11 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00955 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 754 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00586 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 0.000284 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 2.55e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.000807 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.78e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000791 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 2.01e-10 |\n", + "| loss_kl | 8.4e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00267 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 9.76e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 9.62e-10 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00049 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.8e-09 |\n", + "| loss_kl | 0.000191 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.0554 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 756 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 2.54e-10 |\n", + "| loss_kl | 7.93e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.000914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00035 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 9.23e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000706 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 3.06e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000405 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 2.36e-10 |\n", + "| loss_kl | 2.44e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00331 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 9.05e-11 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00399 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 758 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 0.000192 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00602 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000468 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 4.33e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.81e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000998 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 5.06e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | 0.00131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.82e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.424 |\n", + "| loss_vf_loss | 7.45e-10 |\n", + "| loss_kl | 9.2e-05 |\n", + "| loss_ent | 42.4 |\n", + "| ev_tdlam_before | -0.00857 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 0.000181 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | 0.000997 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 6.52e-10 |\n", + "| loss_kl | 5.83e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | 0.00175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 760 |\n", + "| TimestepsSoFar | 1.09e+06 |\n", + "| TimeElapsed | 5.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000457 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 4.61e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.0012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 762 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 5.57e-11 |\n", + "| loss_kl | 8.04e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | 0.0017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 762 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 6.62e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.000861 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 762 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00383 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.00316 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 762 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000878 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 8.08e-11 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | 0.00142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 762 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000919 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 4.2e-10 |\n", + "| loss_kl | 3.6e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.00424 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 2.72e-10 |\n", + "| loss_kl | 8.33e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.0393 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00512 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 3.07e-09 |\n", + "| loss_kl | 0.000358 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.00201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00222 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 8.97e-10 |\n", + "| loss_kl | 0.000205 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000549 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 2.36e-10 |\n", + "| loss_kl | 4.6e-05 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.0623 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000874 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 5.23e-05 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.0207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 764 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000681 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 9.63e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.0433 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.86e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 6.36e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.00863 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00241 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | 0.00125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 4.44e-10 |\n", + "| loss_kl | 6.38e-05 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | 0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.86e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 3.93e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.00218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00424 |\n", + "| loss_pol_entpen | -0.425 |\n", + "| loss_vf_loss | 7.66e-11 |\n", + "| loss_kl | 0.000201 |\n", + "| loss_ent | 42.5 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 766 |\n", + "| TimestepsSoFar | 1.1e+06 |\n", + "| TimeElapsed | 5.87e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000716 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 6.49e-11 |\n", + "| loss_kl | 8.47e-05 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.00535 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.87e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00304 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 4.03e-10 |\n", + "| loss_kl | 0.000177 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | 0.000833 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 2.74e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.00526 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 9.01e-10 |\n", + "| loss_kl | 9.53e-05 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.0761 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 4.96e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0024 |\n", + "| loss_pol_entpen | -0.426 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 8.63e-05 |\n", + "| loss_ent | 42.6 |\n", + "| ev_tdlam_before | -0.0311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 768 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.88e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000858 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 7.53e-10 |\n", + "| loss_kl | 8.64e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 770 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.89e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0006 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 2.47e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 0.00277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 770 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.89e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000913 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 2.25e-10 |\n", + "| loss_kl | 5.64e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.00823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 770 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000556 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 7.68e-10 |\n", + "| loss_kl | 3.4e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 770 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.89e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00242 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 5.03e-10 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.00433 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 770 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00299 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 3.54e-10 |\n", + "| loss_kl | 0.000256 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.00676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 7.34e-10 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.000159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | 5.38e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000865 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 7.36e-11 |\n", + "| loss_kl | 6.65e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 0.00144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00505 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 9.06e-11 |\n", + "| loss_kl | 0.000287 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 0.000627 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00321 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 0.00027 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.000181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 772 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.91e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 1.37e-09 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.92e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000915 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 5.76e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.92e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 6.37e-11 |\n", + "| loss_kl | 7.28e-05 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 3.4e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00538 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 0.000242 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 0.000148 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 0.000451 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0043 |\n", + "| loss_pol_entpen | -0.427 |\n", + "| loss_vf_loss | 7.58e-11 |\n", + "| loss_kl | 0.000291 |\n", + "| loss_ent | 42.7 |\n", + "| ev_tdlam_before | 0.00954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 774 |\n", + "| TimestepsSoFar | 1.11e+06 |\n", + "| TimeElapsed | 5.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0023 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 9.8e-11 |\n", + "| loss_kl | 9.58e-05 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | -0.00596 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | 0.00443 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 0.000204 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | -0.000961 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000948 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 2.5e-10 |\n", + "| loss_kl | 8.4e-05 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | -0.0109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 3.87e-11 |\n", + "| loss_kl | 9.29e-05 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | -0.0419 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00241 |\n", + "| loss_pol_entpen | -0.428 |\n", + "| loss_vf_loss | 6.78e-11 |\n", + "| loss_kl | 0.000146 |\n", + "| loss_ent | 42.8 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 776 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0036 |\n", + "| loss_pol_entpen | -0.429 |\n", + "| loss_vf_loss | 2.77e-10 |\n", + "| loss_kl | 0.000204 |\n", + "| loss_ent | 42.9 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 778 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0031 |\n", + "| loss_pol_entpen | -0.429 |\n", + "| loss_vf_loss | 1.18e-09 |\n", + "| loss_kl | 0.000262 |\n", + "| loss_ent | 42.9 |\n", + "| ev_tdlam_before | -0.00275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 778 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00338 |\n", + "| loss_pol_entpen | -0.429 |\n", + "| loss_vf_loss | 2.29e-09 |\n", + "| loss_kl | 0.000226 |\n", + "| loss_ent | 42.9 |\n", + "| ev_tdlam_before | -0.133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 778 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 7.07e-11 |\n", + "| loss_kl | 0.000265 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | -0.234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 778 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 6.69e-10 |\n", + "| loss_kl | 0.000286 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | -0.0426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 778 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | 0.000226 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.000145 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | -0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | -0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00157 |\n", + "| loss_pol_entpen | -0.43 |\n", + "| loss_vf_loss | 3.55e-10 |\n", + "| loss_kl | 8.46e-05 |\n", + "| loss_ent | 43 |\n", + "| ev_tdlam_before | 0.000679 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000841 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 3.6e-10 |\n", + "| loss_kl | 7.99e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 4.36e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0264 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 780 |\n", + "| TimestepsSoFar | 1.12e+06 |\n", + "| TimeElapsed | 5.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 5.2e-10 |\n", + "| loss_kl | 6.57e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 8.41e-11 |\n", + "| loss_kl | 8.75e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.98e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000536 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 7.52e-11 |\n", + "| loss_kl | 4.97e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.00631 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.98e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | 0.00028 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.99e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000916 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 7.99e-10 |\n", + "| loss_kl | 3.5e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.99e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 7.9e-11 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.00633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 782 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 5.99e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000453 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 2.74e-09 |\n", + "| loss_kl | 2.46e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 3.56e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000604 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 2.06e-10 |\n", + "| loss_kl | 6.48e-05 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0751 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 3.74e-10 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 9.52e-11 |\n", + "| loss_kl | 0.000165 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0388 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 3.14e-10 |\n", + "| loss_kl | 0.000193 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | 0.00214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 784 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000943 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 9.97e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 786 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.01e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 7.57e-10 |\n", + "| loss_kl | 5.16e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.000126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 786 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 8.05e-10 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | 0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 786 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.02e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00314 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 5.38e-10 |\n", + "| loss_kl | 0.000212 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.026 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 786 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00323 |\n", + "| loss_pol_entpen | -0.431 |\n", + "| loss_vf_loss | 2.25e-10 |\n", + "| loss_kl | 0.000196 |\n", + "| loss_ent | 43.1 |\n", + "| ev_tdlam_before | -0.0257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000201 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 786 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 7.73e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00223 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 0.000137 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.0246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000876 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 7.66e-11 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 4.32e-11 |\n", + "| loss_kl | 7.51e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 4.68e-10 |\n", + "| loss_kl | 0.0001 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 5.85e-10 |\n", + "| loss_kl | 0.000178 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000206 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 788 |\n", + "| TimestepsSoFar | 1.13e+06 |\n", + "| TimeElapsed | 6.03e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000426 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 7.33e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.00352 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.04e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 5.5e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.00609 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 5.42e-10 |\n", + "| loss_kl | 7.96e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00468 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 8.57e-11 |\n", + "| loss_kl | 0.000249 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | -0.131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 4.69e-10 |\n", + "| loss_kl | 0.000187 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | 0.000147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000267 |\n", + "| loss_pol_entpen | -0.432 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 8.05e-05 |\n", + "| loss_ent | 43.2 |\n", + "| ev_tdlam_before | 0.004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 790 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.05e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000549 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 5.48e-10 |\n", + "| loss_kl | 7.47e-05 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00265 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 3.92e-10 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | -0.0153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00038 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 2.63e-10 |\n", + "| loss_kl | 5.92e-05 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | 0.00624 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 2.71e-10 |\n", + "| loss_kl | 8.68e-05 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | -0.00492 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 7.93e-05 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | -0.00427 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.433 |\n", + "| loss_vf_loss | 6.93e-11 |\n", + "| loss_kl | 4.29e-05 |\n", + "| loss_ent | 43.3 |\n", + "| ev_tdlam_before | -0.0277 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 792 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.434 |\n", + "| loss_vf_loss | 5.56e-10 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 43.4 |\n", + "| ev_tdlam_before | -0.00844 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 794 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00379 |\n", + "| loss_pol_entpen | -0.434 |\n", + "| loss_vf_loss | 3.24e-10 |\n", + "| loss_kl | 0.000208 |\n", + "| loss_ent | 43.4 |\n", + "| ev_tdlam_before | -0.0178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 794 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.07e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00217 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 9.58e-10 |\n", + "| loss_kl | 0.000199 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | 0.00578 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 794 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000397 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 3.17e-10 |\n", + "| loss_kl | 7.44e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 794 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00222 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 2.03e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.000775 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 794 |\n", + "| TimestepsSoFar | 1.14e+06 |\n", + "| TimeElapsed | 6.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000771 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 8.31e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 7.32e-11 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00104 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 8.84e-11 |\n", + "| loss_kl | 0.000136 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.00249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.09e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 4.99e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.000982 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 4.4e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.00544 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.09e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | 0.00235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000198 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 796 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.1e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000692 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 5.91e-10 |\n", + "| loss_kl | 5.04e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | 0.00303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.44e-09 |\n", + "| loss_kl | 0.000138 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0753 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 2.01e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.11e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000611 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 7.64e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | 0.00226 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.0002 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 798 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000884 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 7.16e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | 0.00287 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.12e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000901 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 5.05e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.00962 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.12e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00214 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 9.58e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.000138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.12e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000911 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 8.37e-11 |\n", + "| loss_kl | 6.38e-05 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0553 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 8.31e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | 0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.435 |\n", + "| loss_vf_loss | 2.64e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 43.5 |\n", + "| ev_tdlam_before | -0.0516 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000202 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 800 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000356 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 3.84e-10 |\n", + "| loss_kl | 4.71e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.00355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 802 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.13e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000701 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 6.79e-11 |\n", + "| loss_kl | 5.15e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0463 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 802 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0032 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 4.93e-10 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.00932 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 802 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 802 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000193 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 802 |\n", + "| TimestepsSoFar | 1.15e+06 |\n", + "| TimeElapsed | 6.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 9.98e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.15e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000393 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 9.14e-11 |\n", + "| loss_kl | 8.24e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0089 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0038 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 7.48e-10 |\n", + "| loss_kl | 0.000145 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.000236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000842 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 1.13e-09 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.15e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 1.04e-09 |\n", + "| loss_kl | 7.52e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.0325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 8.42e-10 |\n", + "| loss_kl | 4e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.00565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 804 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.16e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 8.48e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.000889 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.17e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.000237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.17e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000701 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.000674 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00116 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 3.99e-10 |\n", + "| loss_kl | 7.21e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.000112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00257 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 806 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00876 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 4.31e-11 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 6.48e-11 |\n", + "| loss_kl | 8.7e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00584 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0038 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 8.7e-11 |\n", + "| loss_kl | 0.000174 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.18e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000833 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 6.07e-10 |\n", + "| loss_kl | 4.37e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.000881 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.18e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 3.96e-10 |\n", + "| loss_kl | 0.000128 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 808 |\n", + "| TimestepsSoFar | 1.16e+06 |\n", + "| TimeElapsed | 6.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 2.96e-10 |\n", + "| loss_kl | 5.45e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.000938 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 810 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.2e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 8.16e-11 |\n", + "| loss_kl | 7.09e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 810 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 3.92e-10 |\n", + "| loss_kl | 0.000126 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 810 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 3.87e-10 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.064 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 810 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 6.7e-11 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00611 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 810 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.2e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 8.56e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0334 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00187 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0048 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 0.000279 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.21e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000493 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 4.37e-11 |\n", + "| loss_kl | 5.66e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00414 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.21e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00257 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.22e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00273 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 9.34e-11 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | -0.00188 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 812 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.436 |\n", + "| loss_vf_loss | 7.21e-10 |\n", + "| loss_kl | 8.98e-05 |\n", + "| loss_ent | 43.6 |\n", + "| ev_tdlam_before | 0.000365 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000953 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 8.1e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.085 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000535 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 4.43e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00308 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 9.4e-11 |\n", + "| loss_kl | 9.38e-05 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.00683 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00354 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 0.000207 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | -0.0179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.437 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 43.7 |\n", + "| ev_tdlam_before | 0.00289 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 814 |\n", + "| TimestepsSoFar | 1.17e+06 |\n", + "| TimeElapsed | 6.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 2.89e-10 |\n", + "| loss_kl | 0.00016 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | -0.0136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 4.33e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | 0.00169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00125 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 8.01e-05 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | -0.0601 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.24e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0086 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 2.77e-10 |\n", + "| loss_kl | 0.000448 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | -0.000103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.24e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000315 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000272 |\n", + "| loss_pol_entpen | -0.438 |\n", + "| loss_vf_loss | 7.85e-11 |\n", + "| loss_kl | 3.19e-05 |\n", + "| loss_ent | 43.8 |\n", + "| ev_tdlam_before | -0.00303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 816 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00288 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 4.47e-10 |\n", + "| loss_kl | 0.000203 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | 6.89e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 818 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.26e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000966 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 1.97e-09 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.0768 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 818 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.26e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 1.4e-09 |\n", + "| loss_kl | 9.76e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.0968 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 818 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 1.76e-09 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.0371 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 818 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 4.79e-10 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 818 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 9.44e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.0319 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.27e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 9.55e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | 0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 9.07e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | 0.00163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.27e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 7.72e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.000783 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.28e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00235 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 5.18e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.00237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00231 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 9.78e-11 |\n", + "| loss_kl | 0.000138 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.0552 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 820 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.28e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000808 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 3.31e-10 |\n", + "| loss_kl | 6.18e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.00778 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 8.29e-11 |\n", + "| loss_kl | 0.000148 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.00744 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000165 |\n", + "| loss_pol_entpen | -0.439 |\n", + "| loss_vf_loss | 2.22e-10 |\n", + "| loss_kl | 1.28e-05 |\n", + "| loss_ent | 43.9 |\n", + "| ev_tdlam_before | -0.00528 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0041 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000175 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.00748 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000669 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.01 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 5.06e-11 |\n", + "| loss_kl | 0.000105 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.000583 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 822 |\n", + "| TimestepsSoFar | 1.18e+06 |\n", + "| TimeElapsed | 6.29e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 2.55e-10 |\n", + "| loss_kl | 9.59e-05 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.000685 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00243 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.3e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000847 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 5.53e-10 |\n", + "| loss_kl | 5.57e-05 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.00052 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.3e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0033 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 3e-10 |\n", + "| loss_kl | 0.000191 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.00391 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00195 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 0.000167 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | 0.000168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000643 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 4.58e-05 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 824 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 5.98e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -5.65e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 826 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 4.39e-10 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.0574 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 826 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.32e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00319 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.00362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 826 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 3.78e-10 |\n", + "| loss_kl | 0.000239 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.000935 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 826 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.32e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000478 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 5.6e-05 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.0309 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 826 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 1.02e-09 |\n", + "| loss_kl | 7.31e-05 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | 0.000586 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 5.73e-11 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.0306 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00506 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 8.58e-11 |\n", + "| loss_kl | 0.0003 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.44 |\n", + "| loss_vf_loss | 3.22e-10 |\n", + "| loss_kl | 0.00021 |\n", + "| loss_ent | 44 |\n", + "| ev_tdlam_before | -0.0149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 7.91e-11 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.0442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 7.49e-11 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | 0.00143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 828 |\n", + "| TimestepsSoFar | 1.19e+06 |\n", + "| TimeElapsed | 6.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000727 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.22e-09 |\n", + "| loss_kl | 6.87e-05 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | 0.00162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00336 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 3.33e-09 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.0578 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000678 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 3.48e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.001 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 3.22e-10 |\n", + "| loss_kl | 5.48e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00609 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000102 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 2.36e-10 |\n", + "| loss_kl | 1.72e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.0512 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000633 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 2.72e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00737 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 830 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000631 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 3.81e-05 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.00609 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.36e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000704 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 3.62e-11 |\n", + "| loss_kl | 3.97e-05 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.36e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | -0.000579 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.37e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | 0.000463 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.37e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.441 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 44.1 |\n", + "| ev_tdlam_before | 0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 832 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 7.22e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -1.34e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 834 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 6.47e-11 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 834 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 8.63e-11 |\n", + "| loss_kl | 0.00023 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | 0.000832 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 834 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.38e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0016 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 0.000133 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | 0.00117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 834 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.38e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000693 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 4.21e-10 |\n", + "| loss_kl | 5.76e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -1.97e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 834 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00205 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1e-09 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | 2.77e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 0.000155 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000511 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 6.12e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.042 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00313 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | 0.000911 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00197 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 8.94e-11 |\n", + "| loss_kl | 0.000198 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.0163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000738 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 3.84e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00355 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 836 |\n", + "| TimestepsSoFar | 1.2e+06 |\n", + "| TimeElapsed | 6.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00318 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 6.06e-10 |\n", + "| loss_kl | 0.000164 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.01 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 2.62e-10 |\n", + "| loss_kl | 8.12e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00417 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00195 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 3.38e-10 |\n", + "| loss_kl | 7.51e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | 0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00186 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 0.00012 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.0492 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.41e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000265 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 4.02e-10 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.0235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 838 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.42e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.442 |\n", + "| loss_vf_loss | 5.17e-11 |\n", + "| loss_kl | 8.03e-05 |\n", + "| loss_ent | 44.2 |\n", + "| ev_tdlam_before | -0.00954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0026 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | 0.000865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 5.8e-11 |\n", + "| loss_kl | 0.000141 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.0402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000883 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 9.24e-11 |\n", + "| loss_kl | 7.31e-05 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.00572 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 9.98e-05 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | 0.000254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00238 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 6.51e-11 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.00879 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 840 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.43e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 7.47e-05 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.00601 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 842 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 0.000149 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.00707 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 842 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00253 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 4.85e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 842 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.443 |\n", + "| loss_vf_loss | 6.74e-10 |\n", + "| loss_kl | 0.000166 |\n", + "| loss_ent | 44.3 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 842 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00218 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 2.98e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 842 |\n", + "| TimestepsSoFar | 1.21e+06 |\n", + "| TimeElapsed | 6.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000703 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 6.28e-10 |\n", + "| loss_kl | 6.78e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 5.43e-11 |\n", + "| loss_kl | 7.39e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.0192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000832 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 5.35e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.000843 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000132 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 2.53e-10 |\n", + "| loss_kl | 4.41e-06 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.00472 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000495 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 5.04e-10 |\n", + "| loss_kl | 5.98e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.000458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 844 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00034 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 3.28e-10 |\n", + "| loss_kl | 5.4e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.00475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 6.98e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.00488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.47e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000844 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 2.28e-10 |\n", + "| loss_kl | 5.75e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.00518 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.47e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 5.35e-11 |\n", + "| loss_kl | 7.02e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 4.8e-11 |\n", + "| loss_kl | 5.84e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.00682 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 4.11e-05 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 1.93e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -6.2e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 846 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 5.85e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0499 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 2.05e-10 |\n", + "| loss_kl | 7.43e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 9.14e-11 |\n", + "| loss_kl | 6.82e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.000465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00265 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 9.78e-11 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.000195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.74e-10 |\n", + "| loss_kl | 8.29e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000997 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 7.03e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 848 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.49e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000259 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 1.21e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 850 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000808 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 4.65e-11 |\n", + "| loss_kl | 2.56e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.000195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 850 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 9.9e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.000983 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 850 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.5e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00224 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 7.05e-11 |\n", + "| loss_kl | 7.06e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | -0.0281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 850 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.444 |\n", + "| loss_vf_loss | 4.91e-11 |\n", + "| loss_kl | 8.21e-05 |\n", + "| loss_ent | 44.4 |\n", + "| ev_tdlam_before | 0.000784 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 850 |\n", + "| TimestepsSoFar | 1.22e+06 |\n", + "| TimeElapsed | 6.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 3.47e-10 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0256 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.37e-05 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 7.02e-11 |\n", + "| loss_kl | 4.45e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | 6.23e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00263 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 4.03e-10 |\n", + "| loss_kl | 0.000127 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00848 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1e-09 |\n", + "| loss_kl | 6.97e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000702 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 4.07e-10 |\n", + "| loss_kl | 4.7e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00257 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 7.62e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0444 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 852 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00174 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0444 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00204 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 3.83e-09 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | 0.000631 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.188 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.53e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 9.58e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00715 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 6.51e-10 |\n", + "| loss_kl | 5.11e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 5.72e-11 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 854 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 3.66e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 5.24e-11 |\n", + "| loss_kl | 9.55e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000224 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 3.7e-11 |\n", + "| loss_kl | 2.28e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.000583 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000995 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 4.9e-11 |\n", + "| loss_kl | 5.87e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 3.48e-10 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.000888 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00349 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 0.000186 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 856 |\n", + "| TimestepsSoFar | 1.23e+06 |\n", + "| TimeElapsed | 6.55e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00314 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 6.71e-11 |\n", + "| loss_kl | 0.000171 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.00862 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 858 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0019 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 0.000162 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 858 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.445 |\n", + "| loss_vf_loss | 7.03e-11 |\n", + "| loss_kl | 6.77e-05 |\n", + "| loss_ent | 44.5 |\n", + "| ev_tdlam_before | -0.00482 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 858 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000931 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 6.23e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 858 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 6.59e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.000751 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000194 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 858 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.57e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000769 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 7.6e-11 |\n", + "| loss_kl | 3.74e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -7.32e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00332 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 6.75e-11 |\n", + "| loss_kl | 0.000154 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.000346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000803 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 7.37e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000692 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 5.18e-10 |\n", + "| loss_kl | 4.56e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 7.8e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.0448 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 8.06e-11 |\n", + "| loss_kl | 5.66e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.00404 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000192 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 860 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00356 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.00842 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 4.14e-10 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.00153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00339 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 0.00019 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.00578 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.6e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 5.69e-11 |\n", + "| loss_kl | 9.65e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000561 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 2.32e-10 |\n", + "| loss_kl | 4.59e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.00297 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000501 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 3.98e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | -0.00266 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000197 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 862 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000768 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 1.2e-09 |\n", + "| loss_kl | 3.27e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 0.00127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00442 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 5.23e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.0318 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.003 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 5.4e-10 |\n", + "| loss_kl | 9.42e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00124 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | -0.00456 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000971 |\n", + "| loss_pol_entpen | -0.446 |\n", + "| loss_vf_loss | 5.09e-11 |\n", + "| loss_kl | 7.65e-05 |\n", + "| loss_ent | 44.6 |\n", + "| ev_tdlam_before | 0.00738 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 2.97e-11 |\n", + "| loss_kl | 6.41e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000204 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 864 |\n", + "| TimestepsSoFar | 1.24e+06 |\n", + "| TimeElapsed | 6.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 7.72e-10 |\n", + "| loss_kl | 7.37e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 9.6e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 866 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.62e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000851 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 8.03e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | -0.00716 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 866 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 3.74e-11 |\n", + "| loss_kl | 6.38e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | -0.0248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 866 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.63e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000936 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 6.19e-11 |\n", + "| loss_kl | 5.89e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 0.000849 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 866 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.63e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 4.46e-11 |\n", + "| loss_kl | 4.4e-05 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 866 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00444 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 0.00025 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | 0.00214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000936 |\n", + "| loss_pol_entpen | -0.447 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | 0.000111 |\n", + "| loss_ent | 44.7 |\n", + "| ev_tdlam_before | -0.0472 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.64e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000861 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 5.13e-05 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | -0.0304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.64e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 8.95e-05 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | 0.00335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 7.81e-11 |\n", + "| loss_kl | 9.75e-05 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | 0.00379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 9.38e-11 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | -0.000726 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000208 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 868 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00293 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 0.000211 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 9.84e-11 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | 0.00515 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.65e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000709 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 6.82e-10 |\n", + "| loss_kl | 5.31e-05 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | -0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.66e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00342 |\n", + "| loss_pol_entpen | -0.448 |\n", + "| loss_vf_loss | 9.27e-10 |\n", + "| loss_kl | 0.00017 |\n", + "| loss_ent | 44.8 |\n", + "| ev_tdlam_before | -0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.66e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00537 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 6.23e-10 |\n", + "| loss_kl | 0.000312 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | 0.00889 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.66e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000288 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 3.88e-10 |\n", + "| loss_kl | 8.64e-05 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | -0.0996 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 870 |\n", + "| TimestepsSoFar | 1.25e+06 |\n", + "| TimeElapsed | 6.66e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00157 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 3.98e-10 |\n", + "| loss_kl | 6.19e-05 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | -0.00759 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | 0.00278 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.67e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000992 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 9.95e-11 |\n", + "| loss_kl | 8.21e-05 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | 0.00755 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.67e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | 6.82e-05 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 1.37e-10 |\n", + "| loss_kl | 8.88e-06 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | 0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.67e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000631 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 3.58e-10 |\n", + "| loss_kl | 2.74e-05 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | 0.00156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.67e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.449 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 8.33e-05 |\n", + "| loss_ent | 44.9 |\n", + "| ev_tdlam_before | -0.00405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 872 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | -0.00281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 874 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00382 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 0.000223 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | 0.00773 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 874 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.69e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000689 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 5.65e-11 |\n", + "| loss_kl | 7.81e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | -0.0392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 874 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.69e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 9.17e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | -0.00254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 874 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | 0.00327 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 874 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 7.86e-10 |\n", + "| loss_kl | 9.09e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | -0.00599 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00066 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 3.88e-10 |\n", + "| loss_kl | 7.8e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | 0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 5.02e-11 |\n", + "| loss_kl | 4.66e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | -0.0849 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.7e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000519 |\n", + "| loss_pol_entpen | -0.45 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 45 |\n", + "| ev_tdlam_before | 0 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 5.8e-11 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.0042 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00261 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 0.000168 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000203 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 876 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 9.52e-05 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.00396 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00249 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 5.83e-11 |\n", + "| loss_kl | 7.89e-05 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.00131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0037 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 0.000194 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | 0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 2.48e-11 |\n", + "| loss_kl | 0.000116 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.0671 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 4.58e-11 |\n", + "| loss_kl | 6.07e-05 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.72e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.451 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 8.43e-05 |\n", + "| loss_ent | 45.1 |\n", + "| ev_tdlam_before | -0.00205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 878 |\n", + "| TimestepsSoFar | 1.26e+06 |\n", + "| TimeElapsed | 6.72e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00295 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 3.87e-10 |\n", + "| loss_kl | 0.000161 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | -0.00491 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00472 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 8.35e-10 |\n", + "| loss_kl | 0.000288 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0018 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 5.21e-10 |\n", + "| loss_kl | 0.00018 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00283 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 4.88e-10 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | 0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 2.47e-10 |\n", + "| loss_kl | 0.000173 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | 0.00015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.74e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.452 |\n", + "| loss_vf_loss | 4.04e-10 |\n", + "| loss_kl | 0.000107 |\n", + "| loss_ent | 45.2 |\n", + "| ev_tdlam_before | -0.00337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 880 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000674 |\n", + "| loss_pol_entpen | -0.453 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 5.3e-05 |\n", + "| loss_ent | 45.3 |\n", + "| ev_tdlam_before | 0.000908 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 882 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000592 |\n", + "| loss_pol_entpen | -0.453 |\n", + "| loss_vf_loss | 1.8e-10 |\n", + "| loss_kl | 4.48e-05 |\n", + "| loss_ent | 45.3 |\n", + "| ev_tdlam_before | -0.000688 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 882 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00174 |\n", + "| loss_pol_entpen | -0.453 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 7.7e-05 |\n", + "| loss_ent | 45.3 |\n", + "| ev_tdlam_before | 0.0153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 882 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.75e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.453 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 8.73e-05 |\n", + "| loss_ent | 45.3 |\n", + "| ev_tdlam_before | -0.000492 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 882 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00222 |\n", + "| loss_pol_entpen | -0.453 |\n", + "| loss_vf_loss | 9.29e-11 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 45.3 |\n", + "| ev_tdlam_before | -0.000844 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 882 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 2.29e-10 |\n", + "| loss_kl | 8.49e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00709 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00449 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 0.000152 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000701 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.000495 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.76e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000385 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 6.69e-11 |\n", + "| loss_kl | 8.52e-06 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | 0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 6.27e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00352 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 884 |\n", + "| TimestepsSoFar | 1.27e+06 |\n", + "| TimeElapsed | 6.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000984 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 5.64e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | 0.000794 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000758 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 3.41e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00258 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 4.01e-10 |\n", + "| loss_kl | 9.81e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0411 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000142 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 3.47e-10 |\n", + "| loss_kl | 1.82e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000764 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 5.41e-11 |\n", + "| loss_kl | 3.52e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.042 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00193 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 4.39e-11 |\n", + "| loss_kl | 5.76e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -1.31e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 886 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000767 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 5.96e-10 |\n", + "| loss_kl | 4.68e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000964 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 7.44e-10 |\n", + "| loss_kl | 4.67e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00076 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 2.76e-10 |\n", + "| loss_kl | 4.64e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 6.59e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.79e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 2.65e-08 |\n", + "| loss_kl | 8.25e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | 0.000313 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000691 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.27e-09 |\n", + "| loss_kl | 5.38e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -2.73 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 888 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00014 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.86e-10 |\n", + "| loss_kl | 7.75e-06 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | 0.00159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 890 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 9.84e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.0169 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 890 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000609 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 9.13e-10 |\n", + "| loss_kl | 3.91e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -6.15e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 890 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 4.64e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | 0.00373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 890 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00294 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 4.19e-10 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 890 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.000695 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.82e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 8.9e-05 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00182 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00736 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.82e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.454 |\n", + "| loss_vf_loss | 7.52e-11 |\n", + "| loss_kl | 0.000111 |\n", + "| loss_ent | 45.4 |\n", + "| ev_tdlam_before | -0.00912 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00221 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | 0.000395 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000579 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 4.95e-10 |\n", + "| loss_kl | 6.12e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 892 |\n", + "| TimestepsSoFar | 1.28e+06 |\n", + "| TimeElapsed | 6.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.06e-05 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 1.38e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.0193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00182 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 9.47e-11 |\n", + "| loss_kl | 6.8e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000299 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 3.61e-10 |\n", + "| loss_kl | 3.49e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00062 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 7.31e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0027 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 0.000157 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00563 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000349 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 8.74e-11 |\n", + "| loss_kl | 4.85e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 894 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 3.86e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | 0.00202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.85e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000528 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 7.45e-11 |\n", + "| loss_kl | 4.61e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00255 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 7.32e-11 |\n", + "| loss_kl | 0.000117 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.000864 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00369 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 5.25e-11 |\n", + "| loss_kl | 0.000189 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000504 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 4.55e-11 |\n", + "| loss_kl | 4.45e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | 3.62e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.86e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00291 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 6.13e-11 |\n", + "| loss_kl | 0.00014 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 896 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.86e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00355 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 0.000185 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.00606 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 898 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 3.98e-10 |\n", + "| loss_kl | 0.000142 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 898 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 8.43e-10 |\n", + "| loss_kl | 7.69e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | -0.0171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 898 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.87e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.455 |\n", + "| loss_vf_loss | 3.63e-10 |\n", + "| loss_kl | 6.94e-05 |\n", + "| loss_ent | 45.5 |\n", + "| ev_tdlam_before | 0.00572 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 898 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.87e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000712 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 5.39e-05 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.0107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 898 |\n", + "| TimestepsSoFar | 1.29e+06 |\n", + "| TimeElapsed | 6.87e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000152 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 3.84e-10 |\n", + "| loss_kl | 6.2e-06 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | 9.75e-05 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.00152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00261 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 3.32e-10 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | 0.00425 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 0.000127 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.89e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 2.81e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.000373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000492 |\n", + "| loss_pol_entpen | -0.456 |\n", + "| loss_vf_loss | 3.75e-10 |\n", + "| loss_kl | 5.32e-05 |\n", + "| loss_ent | 45.6 |\n", + "| ev_tdlam_before | -0.00754 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 900 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.89e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00256 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 8.69e-10 |\n", + "| loss_kl | 0.000114 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00281 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 3.27e-10 |\n", + "| loss_kl | 0.000179 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.0549 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 6.64e-11 |\n", + "| loss_kl | 6.3e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 7.56e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.00775 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00262 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 7.46e-11 |\n", + "| loss_kl | 0.000169 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000448 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 8.2e-11 |\n", + "| loss_kl | 1.96e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 902 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000567 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 9.69e-11 |\n", + "| loss_kl | 4.43e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 0.00565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00358 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 0.000129 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 0.00192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000628 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 7.08e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.00155 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.65e-05 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 0.000367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.92e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 0.000139 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 0.000454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.92e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000407 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 3.21e-10 |\n", + "| loss_kl | 7.96e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 4.01e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 904 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.92e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00035 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 4.79e-10 |\n", + "| loss_kl | 7.03e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 906 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.93e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000625 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 3.17e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | 0.00612 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 906 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000957 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 4.5e-10 |\n", + "| loss_kl | 4.92e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.008 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 906 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.93e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.457 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 7.85e-05 |\n", + "| loss_ent | 45.7 |\n", + "| ev_tdlam_before | -0.00653 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 906 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00547 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 906 |\n", + "| TimestepsSoFar | 1.3e+06 |\n", + "| TimeElapsed | 6.93e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00311 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 0.000118 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000678 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 8.17e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.000136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.95e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 5.68e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.95e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000164 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 1.23e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00095 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000833 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.3e-10 |\n", + "| loss_kl | 3.62e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.0194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.95e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 5.99e-11 |\n", + "| loss_kl | 6.32e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.0384 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 908 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.22e-10 |\n", + "| loss_kl | 6.16e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.0253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 9.35e-10 |\n", + "| loss_kl | 9.41e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 4.3e-10 |\n", + "| loss_kl | 9.5e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.97e-05 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.49e-10 |\n", + "| loss_kl | 2.51e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.0379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.96e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00053 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 3.07e-10 |\n", + "| loss_kl | 2.69e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00897 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.96e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 7.34e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.000692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 910 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.37e-10 |\n", + "| loss_kl | 5.26e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.00509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00304 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 0.000143 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.00039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.98e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000891 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 8.49e-11 |\n", + "| loss_kl | 8.54e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.009 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.98e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 5.74e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.98e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00087 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 4.22e-11 |\n", + "| loss_kl | 6.14e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.98e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000514 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.74e-11 |\n", + "| loss_kl | 3.58e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.000157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 912 |\n", + "| TimestepsSoFar | 1.31e+06 |\n", + "| TimeElapsed | 6.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000578 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 4.2e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 914 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 6.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00254 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.000114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 914 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 6.99e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 7.44e-10 |\n", + "| loss_kl | 5.73e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 914 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 6.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 8.96e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | -0.0517 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 914 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 6.99e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.458 |\n", + "| loss_vf_loss | 2.7e-10 |\n", + "| loss_kl | 6.12e-05 |\n", + "| loss_ent | 45.8 |\n", + "| ev_tdlam_before | 0.00438 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 914 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 4.17e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.0537 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000943 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 4.56e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.0012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00246 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 0.000125 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.00178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 3.68e-10 |\n", + "| loss_kl | 8.29e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.00634 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00395 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 0.000195 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.00334 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000892 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 6.32e-11 |\n", + "| loss_kl | 6.06e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 916 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00158 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 5.67e-11 |\n", + "| loss_kl | 8.45e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | 0.00309 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00227 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 2.83e-10 |\n", + "| loss_kl | 0.000108 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.00232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 7.49e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.00951 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 2.7e-10 |\n", + "| loss_kl | 6.37e-05 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | 0.0218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.02e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00195 |\n", + "| loss_pol_entpen | -0.459 |\n", + "| loss_vf_loss | 4.33e-10 |\n", + "| loss_kl | 0.000103 |\n", + "| loss_ent | 45.9 |\n", + "| ev_tdlam_before | -0.0221 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.03e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000429 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 4.77e-11 |\n", + "| loss_kl | 6.09e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | -0.0924 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 918 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.03e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 7.11e-11 |\n", + "| loss_kl | 0.000101 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | -0.0365 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000912 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 8.1e-11 |\n", + "| loss_kl | 2.59e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | 0.009 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 6.87e-11 |\n", + "| loss_kl | 5.52e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | -0.00135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00163 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 6.05e-11 |\n", + "| loss_kl | 8.66e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | 0.00382 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000468 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 2.8e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | 0.000928 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000961 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 3.27e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | 0.00181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 920 |\n", + "| TimestepsSoFar | 1.32e+06 |\n", + "| TimeElapsed | 7.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000685 |\n", + "| loss_pol_entpen | -0.46 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 4.29e-05 |\n", + "| loss_ent | 46 |\n", + "| ev_tdlam_before | 0.00695 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 922 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 5.04e-11 |\n", + "| loss_kl | 0.000131 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | 0.000186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 922 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 6.92e-11 |\n", + "| loss_kl | 6.48e-05 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | -1.2e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 922 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00305 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 9.63e-11 |\n", + "| loss_kl | 0.000156 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | -0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 922 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00364 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 2.22e-10 |\n", + "| loss_kl | 0.000229 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | 0.00387 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 922 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.06e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000702 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 6.34e-10 |\n", + "| loss_kl | 2.93e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 8.85e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000861 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 6.08e-11 |\n", + "| loss_kl | 5.88e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | 0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 8.61e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000326 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 4.88e-11 |\n", + "| loss_kl | 3.15e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.0375 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 4.16e-11 |\n", + "| loss_kl | 5.58e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 924 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.07e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 9.09e-11 |\n", + "| loss_kl | 9.01e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.0448 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.08e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 4.17e-11 |\n", + "| loss_kl | 3.67e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00985 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000977 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 5.14e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.000539 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00226 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 5.41e-11 |\n", + "| loss_kl | 8.86e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000266 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 9.43e-11 |\n", + "| loss_kl | 9.54e-06 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00221 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.09e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000391 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 5.7e-10 |\n", + "| loss_kl | 2.84e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | 0.000197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 926 |\n", + "| TimestepsSoFar | 1.33e+06 |\n", + "| TimeElapsed | 7.09e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000727 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 8.62e-11 |\n", + "| loss_kl | 3.8e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | 0.000506 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000719 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 6.68e-11 |\n", + "| loss_kl | 2.37e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00786 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000804 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 9.86e-11 |\n", + "| loss_kl | 3.12e-05 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | 0.00079 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00174 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 3.63e-11 |\n", + "| loss_kl | 8.25e-05 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | -0.00764 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000919 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 6.79e-05 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | -0.00161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000616 |\n", + "| loss_pol_entpen | -0.461 |\n", + "| loss_vf_loss | 9.03e-10 |\n", + "| loss_kl | 3.78e-05 |\n", + "| loss_ent | 46.1 |\n", + "| ev_tdlam_before | 0.00543 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 928 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00276 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 5.9e-11 |\n", + "| loss_kl | 0.000147 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00576 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 930 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 2.6e-10 |\n", + "| loss_kl | 0.000135 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.00597 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 930 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 8.52e-11 |\n", + "| loss_kl | 8.76e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.0368 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 930 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 8.89e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.0431 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 930 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000936 |\n", + "| loss_pol_entpen | -0.462 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 6.82e-05 |\n", + "| loss_ent | 46.2 |\n", + "| ev_tdlam_before | -0.014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 930 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 5.2e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.0174 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00134 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 3.6e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00875 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 6.57e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.000652 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00248 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 8.18e-11 |\n", + "| loss_kl | 7.62e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.000656 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00307 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.0106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 0.000129 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 2.1e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 932 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 9.67e-11 |\n", + "| loss_kl | 5.63e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.00401 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 6.28e-11 |\n", + "| loss_kl | 6.46e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00575 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 4.75e-11 |\n", + "| loss_kl | 5.23e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.000353 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 9.25e-11 |\n", + "| loss_kl | 0.00011 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.000189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 6.62e-11 |\n", + "| loss_kl | 5.59e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.15e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 3.47e-11 |\n", + "| loss_kl | 2.08e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00621 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 934 |\n", + "| TimestepsSoFar | 1.34e+06 |\n", + "| TimeElapsed | 7.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000282 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 4.59e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000605 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 7.88e-11 |\n", + "| loss_kl | 2.05e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00423 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000935 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 5.03e-11 |\n", + "| loss_kl | 4.4e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.00455 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00328 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 0.000127 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00395 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 8.76e-11 |\n", + "| loss_kl | 0.000132 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.0311 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000279 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 5.77e-11 |\n", + "| loss_kl | 2.87e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.0204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 936 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 3.79e-10 |\n", + "| loss_kl | 0.0001 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.0242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 938 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.17e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0029 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 4.9e-11 |\n", + "| loss_kl | 0.000124 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -9.67e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 938 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00149 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 5.9e-10 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.00696 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 938 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.18e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 5.88e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.00988 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 938 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 3.77e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | -0.0633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000214 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 938 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.18e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 5.61e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 7.04e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.463 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 4.94e-05 |\n", + "| loss_ent | 46.3 |\n", + "| ev_tdlam_before | 0.00203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000468 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 8.54e-11 |\n", + "| loss_kl | 4.41e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00292 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 5.44e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00181 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 4.62e-10 |\n", + "| loss_kl | 0.000121 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00247 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 7.78e-11 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 940 |\n", + "| TimestepsSoFar | 1.35e+06 |\n", + "| TimeElapsed | 7.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000941 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 2.86e-10 |\n", + "| loss_kl | 6.47e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000392 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 2.66e-10 |\n", + "| loss_kl | 1.03e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00702 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000383 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 5.93e-11 |\n", + "| loss_kl | 2.05e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 0.0475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.21e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000924 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 2.87e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -6.52e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.21e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000954 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 7.27e-11 |\n", + "| loss_kl | 3.19e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.21e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 4.03e-05 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 4.85e-11 |\n", + "| loss_kl | 6.26e-06 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 0.00223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 942 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.21e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 8.13e-11 |\n", + "| loss_kl | 4.82e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 8.67e-11 |\n", + "| loss_kl | 6.13e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 6.31e-11 |\n", + "| loss_kl | 3.05e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 6.43e-11 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 8.07e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 0.000258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00356 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 3.73e-10 |\n", + "| loss_kl | 0.000151 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | 0.00229 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 944 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.22e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00337 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 5.78e-10 |\n", + "| loss_kl | 0.000112 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00562 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 946 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.23e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00047 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 6.46e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00297 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 946 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.24e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000351 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 3.45e-10 |\n", + "| loss_kl | 2.06e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.0197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 946 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.24e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000536 |\n", + "| loss_pol_entpen | -0.464 |\n", + "| loss_vf_loss | 6.58e-10 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 46.4 |\n", + "| ev_tdlam_before | -0.00298 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 946 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.24e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00327 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 3.09e-10 |\n", + "| loss_kl | 0.000134 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.0132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 946 |\n", + "| TimestepsSoFar | 1.36e+06 |\n", + "| TimeElapsed | 7.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 7.75e-11 |\n", + "| loss_kl | 4.94e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | 0.0152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000784 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 5.98e-11 |\n", + "| loss_kl | 2.3e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00565 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000991 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 4.42e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | 0.000726 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 3.71e-10 |\n", + "| loss_kl | 4.26e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.25e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000562 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 3.79e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00315 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 5.13e-10 |\n", + "| loss_kl | 0.000122 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00489 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 948 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.26e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000688 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 2.28e-10 |\n", + "| loss_kl | 4.55e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00576 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.26e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000544 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 1.83e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | 0.00473 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.27e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000678 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 2.56e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.000479 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.27e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 9.25e-10 |\n", + "| loss_kl | 8.37e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.27e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000819 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 3.64e-10 |\n", + "| loss_kl | 4.42e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.00462 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.27e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.465 |\n", + "| loss_vf_loss | 8.04e-11 |\n", + "| loss_kl | 5.59e-05 |\n", + "| loss_ent | 46.5 |\n", + "| ev_tdlam_before | -0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 950 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.27e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 8.55e-11 |\n", + "| loss_kl | 6.82e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | 0.000866 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.28e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 7.28e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | 0.00272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 4.18e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.00312 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 7.98e-10 |\n", + "| loss_kl | 3.74e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.28e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 5.88e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.0241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.28e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000665 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 3.17e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.0195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 952 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 3.88e-11 |\n", + "| loss_kl | 8.48e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.00378 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 954 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 8.95e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.00152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 954 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 6.02e-11 |\n", + "| loss_kl | 4.38e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | 0.000102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 954 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.3e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.22e-05 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 7.06e-11 |\n", + "| loss_kl | 1.45e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 954 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.3e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 5.76e-11 |\n", + "| loss_kl | 2.89e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | 0.00151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000218 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 954 |\n", + "| TimestepsSoFar | 1.37e+06 |\n", + "| TimeElapsed | 7.3e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 0.000115 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | -0.00438 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 3.45e-10 |\n", + "| loss_kl | 8.06e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.000659 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0009 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 2.91e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000814 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 2.49e-10 |\n", + "| loss_kl | 4.82e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.00268 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000923 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 2.15e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.00603 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00046 |\n", + "| loss_pol_entpen | -0.466 |\n", + "| loss_vf_loss | 6.27e-11 |\n", + "| loss_kl | 2.62e-05 |\n", + "| loss_ent | 46.6 |\n", + "| ev_tdlam_before | 0.00178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 956 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 8.39e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 3.11e-10 |\n", + "| loss_kl | 6.54e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.001 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0028 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 2.96e-10 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0187 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 0.000113 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0665 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000505 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 8e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.0379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 7.64e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 958 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 2.8e-10 |\n", + "| loss_kl | 9.3e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.00854 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000518 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 8.3e-11 |\n", + "| loss_kl | 1.47e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0264 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.34e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00143 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 5.57e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.0231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000608 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 3.93e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.00379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.34e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000423 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 2.12e-10 |\n", + "| loss_kl | 2.73e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | 0.000773 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000644 |\n", + "| loss_pol_entpen | -0.467 |\n", + "| loss_vf_loss | 7.7e-11 |\n", + "| loss_kl | 2.36e-05 |\n", + "| loss_ent | 46.7 |\n", + "| ev_tdlam_before | -0.000651 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 960 |\n", + "| TimestepsSoFar | 1.38e+06 |\n", + "| TimeElapsed | 7.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 0.00015 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 962 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000515 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 7.15e-11 |\n", + "| loss_kl | 3.52e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.000964 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 962 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.36e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000825 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 3.97e-11 |\n", + "| loss_kl | 2.97e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.000526 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 962 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 4.74e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 962 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00066 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 5.92e-11 |\n", + "| loss_kl | 3.71e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0539 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 962 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000662 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 2.76e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.37e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00156 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 5.05e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.61e-05 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 4.89e-10 |\n", + "| loss_kl | 1.88e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.000108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.37e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000863 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 6.86e-10 |\n", + "| loss_kl | 3.2e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00848 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 2.78e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.38e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000836 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 9.48e-11 |\n", + "| loss_kl | 3.44e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.000488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 964 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 8.64e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000309 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 2.48e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00381 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000653 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 2.23e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00287 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 7.75e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -8.95e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000956 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 5.54e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.012 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000723 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 2.96e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.000692 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 966 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.39e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 6.6e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00518 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 3.32e-10 |\n", + "| loss_kl | 4.6e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00915 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000494 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 2.59e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00585 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.4e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000166 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 5.3e-06 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0359 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.41e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000444 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 4.53e-11 |\n", + "| loss_kl | 2.46e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.41e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.33e-10 |\n", + "| loss_kl | 5.38e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 968 |\n", + "| TimestepsSoFar | 1.39e+06 |\n", + "| TimeElapsed | 7.41e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00241 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 0.000119 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 970 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.42e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -2.9e-06 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 3.9e-10 |\n", + "| loss_kl | 1.47e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00448 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 970 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000528 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.97e-10 |\n", + "| loss_kl | 2.93e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 970 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.42e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 4.77e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0292 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 970 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000408 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 8.9e-11 |\n", + "| loss_kl | 3.34e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00463 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 970 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.42e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000744 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 2.32e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.43e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 3.64e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 5.05e-11 |\n", + "| loss_kl | 0.000106 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.000748 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00208 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 6.28e-11 |\n", + "| loss_kl | 9.42e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.44e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000329 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 2.22e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00083 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.44e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 2.76e-10 |\n", + "| loss_kl | 3.53e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 972 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.32e-10 |\n", + "| loss_kl | 8.62e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | 0.00314 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00097 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 5.38e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000832 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 2.32e-10 |\n", + "| loss_kl | 4.06e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00506 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000585 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 8.27e-11 |\n", + "| loss_kl | 3.12e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.0416 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 8.2e-11 |\n", + "| loss_kl | 4.27e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -8.81e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00184 |\n", + "| loss_pol_entpen | -0.468 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 8.7e-05 |\n", + "| loss_ent | 46.8 |\n", + "| ev_tdlam_before | -0.00059 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 974 |\n", + "| TimestepsSoFar | 1.4e+06 |\n", + "| TimeElapsed | 7.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 5.06e-10 |\n", + "| loss_kl | 9.55e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.000555 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000909 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 7.75e-11 |\n", + "| loss_kl | 4.4e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00561 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 2.75e-10 |\n", + "| loss_kl | 9.48e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.46e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000525 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 5.1e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.47e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00207 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 5.46e-11 |\n", + "| loss_kl | 8.4e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 7.99e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.00113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 976 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 9.74e-11 |\n", + "| loss_kl | 5.25e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.000194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 978 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00076 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 9.62e-11 |\n", + "| loss_kl | 5.95e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 978 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.48e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000781 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 4.51e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.000823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 978 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00346 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 4.31e-10 |\n", + "| loss_kl | 9.04e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00899 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 978 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000728 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 6.56e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0323 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 978 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00157 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 6.11e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.00029 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.49e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.86e-10 |\n", + "| loss_kl | 6.75e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.000474 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.5e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000441 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 6.4e-11 |\n", + "| loss_kl | 3.12e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.000411 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00252 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 6.64e-10 |\n", + "| loss_kl | 9.11e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.000616 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000955 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 4.3e-10 |\n", + "| loss_kl | 6.29e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.5e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 6.25e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00336 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 980 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 8.22e-11 |\n", + "| loss_kl | 5.05e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00266 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 7.6e-11 |\n", + "| loss_kl | 9.48e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0352 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.51e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 8.07e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.00178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.51e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000639 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 5.06e-10 |\n", + "| loss_kl | 4.61e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -3.58e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000971 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 2.66e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.00096 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00165 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 8.46e-11 |\n", + "| loss_kl | 8.2e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.026 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 982 |\n", + "| TimestepsSoFar | 1.41e+06 |\n", + "| TimeElapsed | 7.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 6.38e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.52e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 5.47e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.53e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000756 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 6.51e-11 |\n", + "| loss_kl | 3.3e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.00976 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.53e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00237 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 6.65e-11 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.00348 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.53e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000421 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 6.56e-10 |\n", + "| loss_kl | 4.39e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | 0.000413 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000583 |\n", + "| loss_pol_entpen | -0.469 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 3.02e-05 |\n", + "| loss_ent | 46.9 |\n", + "| ev_tdlam_before | -0.0724 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 984 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000348 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 1.09e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 9.1e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 986 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000294 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 9.45e-10 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 986 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00257 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 6.13e-10 |\n", + "| loss_kl | 8.11e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.0045 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 986 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000959 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 6.77e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.0253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 986 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000139 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 1.65e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.00444 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 986 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.55e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 4.83e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.000823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00184 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 2.44e-10 |\n", + "| loss_kl | 8.12e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.00719 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00127 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 7.5e-11 |\n", + "| loss_kl | 4.44e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.0382 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00081 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 8.28e-11 |\n", + "| loss_kl | 4.32e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.00124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000752 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 4.17e-11 |\n", + "| loss_kl | 4.04e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.000211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 6.25e-11 |\n", + "| loss_kl | 4.58e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.0061 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 988 |\n", + "| TimestepsSoFar | 1.42e+06 |\n", + "| TimeElapsed | 7.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 0.000144 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00375 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 0.000184 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000171 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 8.03e-11 |\n", + "| loss_kl | 4.02e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | 0.00345 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000962 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 3.26e-10 |\n", + "| loss_kl | 2.67e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00045 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.57e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 6.1e-11 |\n", + "| loss_kl | 5.66e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00306 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00174 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 1.94e-10 |\n", + "| loss_kl | 6.79e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00863 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 990 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.58e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0009 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 3.7e-10 |\n", + "| loss_kl | 4.9e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.58e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.47 |\n", + "| loss_vf_loss | 6.46e-10 |\n", + "| loss_kl | 6.53e-05 |\n", + "| loss_ent | 47 |\n", + "| ev_tdlam_before | -0.0191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 2.78e-10 |\n", + "| loss_kl | 5.2e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 5.54e-11 |\n", + "| loss_kl | 4.81e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.00476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.59e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00183 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 2.88e-10 |\n", + "| loss_kl | 8.41e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0278 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.59e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000918 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 2.19e-10 |\n", + "| loss_kl | 4.66e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000248 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 992 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.59e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 3.87e-11 |\n", + "| loss_kl | 4.81e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 9.24e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 994 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 4.48e-11 |\n", + "| loss_kl | 5.22e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.000102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 994 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 4.56e-11 |\n", + "| loss_kl | 4.49e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.00435 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 994 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000336 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 7.96e-11 |\n", + "| loss_kl | 3.21e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.000831 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 994 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 6.33e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.00238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000249 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 994 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.61e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000802 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 2.89e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0053 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000709 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 4.61e-10 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.000748 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000843 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 3.05e-10 |\n", + "| loss_kl | 3.81e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000974 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 3.39e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00139 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 5.03e-10 |\n", + "| loss_kl | 6.88e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.00383 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00223 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 8.54e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 996 |\n", + "| TimestepsSoFar | 1.43e+06 |\n", + "| TimeElapsed | 7.62e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00239 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 7.89e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0084 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.63e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000812 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 5.61e-11 |\n", + "| loss_kl | 3.7e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | 0.0167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.63e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000678 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 7.16e-11 |\n", + "| loss_kl | 1.86e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0099 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.63e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 6.38e-11 |\n", + "| loss_kl | 8.01e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.00879 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00225 |\n", + "| loss_pol_entpen | -0.471 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 9.42e-05 |\n", + "| loss_ent | 47.1 |\n", + "| ev_tdlam_before | -0.0114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00302 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 0.000153 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.00581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 998 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000821 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 3.08e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | 4.27e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 3.66e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.00144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00021 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 7.23e-10 |\n", + "| loss_kl | 2.07e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000261 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 8.52e-06 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | 3.88e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0671 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 7.93e-11 |\n", + "| loss_kl | 8.02e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000241 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 4.26e-11 |\n", + "| loss_kl | 4.45e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.66e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 5.26e-10 |\n", + "| loss_kl | 4.24e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.000489 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000232 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 3.52e-11 |\n", + "| loss_kl | 2.44e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.0315 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.67e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 6.99e-11 |\n", + "| loss_kl | 6.69e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -2.81e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.67e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000704 |\n", + "| loss_pol_entpen | -0.472 |\n", + "| loss_vf_loss | 6.44e-11 |\n", + "| loss_kl | 3.59e-05 |\n", + "| loss_ent | 47.2 |\n", + "| ev_tdlam_before | -0.00141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.44e+06 |\n", + "| TimeElapsed | 7.67e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000283 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | 0.000847 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00151 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 4.61e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | 0.00458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000527 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 1.98e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.00397 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 3.66e-10 |\n", + "| loss_kl | 5.75e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.00191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 5.76e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000308 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 2.86e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | 0.000507 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00171 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 6.88e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 7.8e-10 |\n", + "| loss_kl | 7.49e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | 0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 4.83e-11 |\n", + "| loss_kl | 6.38e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.69e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00179 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 2.94e-10 |\n", + "| loss_kl | 7.55e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | 0.00224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.7e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000108 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 8.1e-10 |\n", + "| loss_kl | 2.25e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.7e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000863 |\n", + "| loss_pol_entpen | -0.473 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 3.18e-05 |\n", + "| loss_ent | 47.3 |\n", + "| ev_tdlam_before | -0.0426 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00236 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 7.77e-10 |\n", + "| loss_kl | 0.000119 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | 0.00138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 3.1e-10 |\n", + "| loss_kl | 7.3e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.179 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000315 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 2.22e-10 |\n", + "| loss_kl | 2.71e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0342 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 3.13e-10 |\n", + "| loss_kl | 3.67e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0476 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000464 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 4.99e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0922 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 9.68e-11 |\n", + "| loss_kl | 6.07e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0297 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.71e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.75e-05 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.000731 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.72e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00334 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 9.83e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.73e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 0.000102 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.73e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000796 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 4.84e-11 |\n", + "| loss_kl | 3.96e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.73e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00244 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 2.73e-10 |\n", + "| loss_kl | 0.000111 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.45e+06 |\n", + "| TimeElapsed | 7.73e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000935 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 2.37e-10 |\n", + "| loss_kl | 3.97e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000752 |\n", + "| loss_pol_entpen | -0.474 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 2.41e-05 |\n", + "| loss_ent | 47.4 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000769 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 9.58e-11 |\n", + "| loss_kl | 4.86e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | 0.0021 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 3.53e-11 |\n", + "| loss_kl | 5.67e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | -0.000288 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 7.66e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | -0.000205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000827 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 2.45e-10 |\n", + "| loss_kl | 4.93e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | 0.00309 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00104 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 9.87e-11 |\n", + "| loss_kl | 6.13e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | -0.00115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.75e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.475 |\n", + "| loss_vf_loss | 3.63e-11 |\n", + "| loss_kl | 6.43e-05 |\n", + "| loss_ent | 47.5 |\n", + "| ev_tdlam_before | -0.00747 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0025 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 0.000109 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00167 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.31e-05 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.0238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.76e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00322 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 5.52e-11 |\n", + "| loss_kl | 9.7e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.0254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000725 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 3.57e-11 |\n", + "| loss_kl | 4.98e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.01e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.76e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000692 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 3.15e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00515 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.77e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000301 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00137 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 5.26e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00155 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.78e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000953 |\n", + "| loss_pol_entpen | -0.476 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 4.21e-05 |\n", + "| loss_ent | 47.6 |\n", + "| ev_tdlam_before | -0.00913 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.78e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 5.31e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.00606 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.78e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000422 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 4.23e-10 |\n", + "| loss_kl | 3.14e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.0101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.46e+06 |\n", + "| TimeElapsed | 7.78e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 2.01e-10 |\n", + "| loss_kl | 4.32e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.00365 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.79e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 9.06e-11 |\n", + "| loss_kl | 3.17e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.0153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000675 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 7.37e-11 |\n", + "| loss_kl | 3.92e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | 0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000746 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 6.61e-10 |\n", + "| loss_kl | 2.48e-05 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.00573 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 2.26e-05 |\n", + "| loss_pol_entpen | -0.477 |\n", + "| loss_vf_loss | 5.99e-10 |\n", + "| loss_kl | 9.89e-06 |\n", + "| loss_ent | 47.7 |\n", + "| ev_tdlam_before | -0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000357 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 2.67e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0389 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000268 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 8.29e-11 |\n", + "| loss_kl | 1.49e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0354 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000786 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 3.92e-10 |\n", + "| loss_kl | 3.02e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.00227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 8.15e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.81e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00092 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 6.13e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0196 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.81e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00518 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 0.000163 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.000214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.81e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00184 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 6.43e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.82e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00016 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 4.18e-11 |\n", + "| loss_kl | 3.49e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000586 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.65e-10 |\n", + "| loss_kl | 2.14e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.00372 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00063 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 3.15e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00469 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 6.72e-11 |\n", + "| loss_kl | 4.02e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.00689 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.83e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00162 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 4.17e-10 |\n", + "| loss_kl | 7.14e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00445 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000581 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 2.86e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00499 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 3.04e-10 |\n", + "| loss_kl | 4.26e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.000527 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.84e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00226 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.8e-10 |\n", + "| loss_kl | 9.07e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.84e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000799 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 4.46e-10 |\n", + "| loss_kl | 5.23e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.00212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.84e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 9.41e-10 |\n", + "| loss_kl | 4.86e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00308 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 9.1e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.02e+03 |\n", + "| TimestepsSoFar | 1.47e+06 |\n", + "| TimeElapsed | 7.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 7.94e-10 |\n", + "| loss_kl | 6.03e-05 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | 0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000814 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 8.09e-10 |\n", + "| loss_kl | 3.73e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0703 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.86e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00233 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 6.61e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.00398 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00209 |\n", + "| loss_pol_entpen | -0.478 |\n", + "| loss_vf_loss | 7.07e-11 |\n", + "| loss_kl | 0.000104 |\n", + "| loss_ent | 47.8 |\n", + "| ev_tdlam_before | -0.000676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.87e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000948 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 2.16e-10 |\n", + "| loss_kl | 4.08e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.00267 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.87e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00384 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 0.00013 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.00409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000768 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 7.52e-11 |\n", + "| loss_kl | 6.25e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | 0.00574 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000364 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 7e-11 |\n", + "| loss_kl | 2.16e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 2.86e-10 |\n", + "| loss_kl | 2.47e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | 0.000754 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000624 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 4.18e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0226 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000533 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 8.65e-11 |\n", + "| loss_kl | 1.44e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0021 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 9.28e-11 |\n", + "| loss_kl | 4.96e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.89e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000371 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 5.64e-11 |\n", + "| loss_kl | 4.09e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.89e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 5.26e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -5.2e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.89e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 4.68e-10 |\n", + "| loss_kl | 7.53e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.9e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000866 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 4.54e-10 |\n", + "| loss_kl | 4.2e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | 0.00571 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.9e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000623 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 2.73e-10 |\n", + "| loss_kl | 3.05e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.48e+06 |\n", + "| TimeElapsed | 7.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000321 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 3.3e-10 |\n", + "| loss_kl | 9.83e-06 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.00456 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000577 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 7.93e-11 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.000462 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00213 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 5.69e-11 |\n", + "| loss_kl | 7.41e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.00184 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000499 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 2.63e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00122 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 4.27e-11 |\n", + "| loss_kl | 4.32e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | 0.000229 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00119 |\n", + "| loss_pol_entpen | -0.479 |\n", + "| loss_vf_loss | 6.4e-11 |\n", + "| loss_kl | 4.09e-05 |\n", + "| loss_ent | 47.9 |\n", + "| ev_tdlam_before | -0.014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.91e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 5.89e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.92e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00154 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 5.65e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.00568 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.92e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000175 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 1.4e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00552 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000896 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.53e-11 |\n", + "| loss_kl | 2.68e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -8.27e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000666 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 2.84e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.03e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000856 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 4.34e-10 |\n", + "| loss_kl | 3e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0022 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 7.01e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00671 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000919 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 4.65e-11 |\n", + "| loss_kl | 4.97e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.00406 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 8.41e-11 |\n", + "| loss_kl | 5.39e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000187 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.000752 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00104 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 3.03e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.00231 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000631 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.51e-10 |\n", + "| loss_kl | 2.29e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.95e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 7.91e-10 |\n", + "| loss_kl | 4.36e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.0406 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.95e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 3.78e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0282 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000617 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | 2e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.00178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.96e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.14e-10 |\n", + "| loss_kl | 4.47e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000669 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 9.15e-10 |\n", + "| loss_kl | 3.46e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.49e+06 |\n", + "| TimeElapsed | 7.96e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000928 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 2.58e-11 |\n", + "| loss_kl | 5.62e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.000622 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000275 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.06e-11 |\n", + "| loss_kl | 9.6e-06 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00441 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.44e-11 |\n", + "| loss_kl | 3.42e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 4.73e-11 |\n", + "| loss_kl | 4.27e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.00161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000782 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 5.75e-11 |\n", + "| loss_kl | 2.49e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | 0.0015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000423 |\n", + "| loss_pol_entpen | -0.48 |\n", + "| loss_vf_loss | 4.09e-11 |\n", + "| loss_kl | 1.93e-05 |\n", + "| loss_ent | 48 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000792 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 5.18e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | 0.00153 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.98e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00191 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 5.38e-10 |\n", + "| loss_kl | 5.88e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00493 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.99e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000708 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 5.02e-10 |\n", + "| loss_kl | 5.34e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | 0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000674 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 3.25e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.0365 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000879 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 2.71e-10 |\n", + "| loss_kl | 3.12e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00334 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 7.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000501 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 9.77e-11 |\n", + "| loss_kl | 1.7e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | 0.000918 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00099 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 3.1e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000887 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 2.14e-10 |\n", + "| loss_kl | 3.31e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00727 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000818 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 3.41e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | 0.00039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000527 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 2.53e-10 |\n", + "| loss_kl | 2.59e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.0097 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000431 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 2.82e-10 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.0159 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.04e+03 |\n", + "| TimestepsSoFar | 1.5e+06 |\n", + "| TimeElapsed | 8.01e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00023 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 2.17e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.0225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 2.05e-10 |\n", + "| loss_kl | 3.75e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | 2.06e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.01e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 1.74e-10 |\n", + "| loss_kl | 4.97e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00597 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.02e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00189 |\n", + "| loss_pol_entpen | -0.481 |\n", + "| loss_vf_loss | 3.42e-10 |\n", + "| loss_kl | 7.89e-05 |\n", + "| loss_ent | 48.1 |\n", + "| ev_tdlam_before | -0.00896 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.02e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000197 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 5.21e-10 |\n", + "| loss_kl | 2.15e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.0196 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.02e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.33e-10 |\n", + "| loss_kl | 3.09e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.00185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.02e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000538 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 2.26e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.00317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000658 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 6.71e-10 |\n", + "| loss_kl | 2.3e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.00513 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000379 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 1.42e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.0038 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 2.12e-10 |\n", + "| loss_kl | 2.05e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.000729 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000749 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 2.12e-10 |\n", + "| loss_kl | 2.5e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.000777 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000612 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 4.12e-10 |\n", + "| loss_kl | 3.1e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.0126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000999 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 6.41e-11 |\n", + "| loss_kl | 4.81e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.14 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.04e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0017 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 4.01e-11 |\n", + "| loss_kl | 6.36e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.00868 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000198 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 3.25e-11 |\n", + "| loss_kl | 1.65e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.00588 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 2.85e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.000152 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.05e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 8.24e-11 |\n", + "| loss_kl | 4.36e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | 0.00131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000246 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.05e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00272 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.38e-09 |\n", + "| loss_kl | 8.07e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.00123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00196 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 9.86e-11 |\n", + "| loss_kl | 7.87e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00168 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 5.76e-10 |\n", + "| loss_kl | 8.76e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.00373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.06e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000672 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 3.61e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.06e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000778 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 9.48e-11 |\n", + "| loss_kl | 2.94e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.0134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.07e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000741 |\n", + "| loss_pol_entpen | -0.482 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 2.77e-05 |\n", + "| loss_ent | 48.2 |\n", + "| ev_tdlam_before | -0.000335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.51e+06 |\n", + "| TimeElapsed | 8.07e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000712 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 3.2e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.0947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.07e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000152 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 1.6e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.0247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 2.61e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | 0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000444 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 3.26e-10 |\n", + "| loss_kl | 2.16e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.00336 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.08e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00242 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 2.3e-10 |\n", + "| loss_kl | 7.96e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.00265 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.08e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000773 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 2.51e-10 |\n", + "| loss_kl | 4.98e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.05e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000883 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 3.29e-10 |\n", + "| loss_kl | 2.46e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.00772 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 4.09e-11 |\n", + "| loss_kl | 4.26e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | 0.0286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.09e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000297 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 7.37e-11 |\n", + "| loss_kl | 2.01e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.000885 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00186 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 3.56e-11 |\n", + "| loss_kl | 5.52e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | 0.00146 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.09e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 4.65e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.000957 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.1e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00044 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 7.33e-11 |\n", + "| loss_kl | 2.24e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | 0.00594 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.1e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00161 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | 4.12e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | 0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.11e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00076 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 2.85e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.0181 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.11e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00012 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 5.82e-11 |\n", + "| loss_kl | 1.31e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.000571 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000615 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 3.38e-10 |\n", + "| loss_kl | 1.47e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.000149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000735 |\n", + "| loss_pol_entpen | -0.483 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 2.82e-05 |\n", + "| loss_ent | 48.3 |\n", + "| ev_tdlam_before | -0.0273 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.52e+06 |\n", + "| TimeElapsed | 8.11e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 5.87e-10 |\n", + "| loss_kl | 4.08e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | 0.0025 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000348 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 8.77e-11 |\n", + "| loss_kl | 2.22e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 2.21e-10 |\n", + "| loss_kl | 3.73e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | -0.00454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.12e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00206 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 4.59e-10 |\n", + "| loss_kl | 8.52e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | 0.00768 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000281 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 2.5e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | -0.058 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.13e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00194 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 4.57e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | 0.00413 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000245 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.13e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000698 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 4.29e-10 |\n", + "| loss_kl | 1.79e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 0.0023 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000286 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 6.64e-11 |\n", + "| loss_kl | 1.7e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.0391 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 6.24e-11 |\n", + "| loss_kl | 4.86e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 0.0176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000476 |\n", + "| loss_pol_entpen | -0.484 |\n", + "| loss_vf_loss | 2.12e-10 |\n", + "| loss_kl | 1.96e-05 |\n", + "| loss_ent | 48.4 |\n", + "| ev_tdlam_before | 0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 2.87e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.0133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00211 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 7.19e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.14e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000706 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 3.02e-10 |\n", + "| loss_kl | 2.26e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000974 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 3.36e-10 |\n", + "| loss_kl | 2.71e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 0.00054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.15e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00153 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 5.7e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 0.00485 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.15e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 4.37e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.00609 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.16e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000567 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 4.7e-11 |\n", + "| loss_kl | 3.78e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.00241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 4.49e-11 |\n", + "| loss_kl | 5.13e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.000206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.06e+03 |\n", + "| TimestepsSoFar | 1.53e+06 |\n", + "| TimeElapsed | 8.16e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000403 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 2.69e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.0531 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.17e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000482 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 7.43e-11 |\n", + "| loss_kl | 1.8e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.00832 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 3.67e-05 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | 2.14e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.17e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.98e-06 |\n", + "| loss_pol_entpen | -0.485 |\n", + "| loss_vf_loss | 4.94e-11 |\n", + "| loss_kl | 7.57e-06 |\n", + "| loss_ent | 48.5 |\n", + "| ev_tdlam_before | -0.00716 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00216 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 5.04e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00616 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00039 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 3.18e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.18e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000747 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 3.67e-10 |\n", + "| loss_kl | 2.21e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00434 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.18e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 5.28e-10 |\n", + "| loss_kl | 3.56e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0483 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000281 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 5.76e-11 |\n", + "| loss_kl | 2.39e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00726 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.19e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000738 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 1.57e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.000458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.19e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00127 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 4.78e-11 |\n", + "| loss_kl | 4.36e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00595 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000767 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 3.45e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00735 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000471 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 2.87e-10 |\n", + "| loss_kl | 1.96e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.000326 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 8.38e-11 |\n", + "| loss_kl | 3.25e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0038 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000969 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 3.02e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000553 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 3.48e-11 |\n", + "| loss_kl | 2.25e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.000487 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000853 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 3.32e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.000337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000656 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 5.76e-10 |\n", + "| loss_kl | 1.69e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0024 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.21e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000562 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 9.88e-11 |\n", + "| loss_kl | 1.77e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.21e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000585 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 6.11e-11 |\n", + "| loss_kl | 2.37e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0292 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.22e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000368 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 1.68e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 3.71e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00146 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 3.39e-11 |\n", + "| loss_kl | 3.81e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.22e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000477 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 8.66e-11 |\n", + "| loss_kl | 3.19e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00711 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.54e+06 |\n", + "| TimeElapsed | 8.22e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 2.95e-05 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.59e-10 |\n", + "| loss_kl | 6.56e-06 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00554 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000696 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 1.31e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.23e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00192 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 6.22e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00357 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.23e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000587 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 5.79e-11 |\n", + "| loss_kl | 3.47e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0645 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000424 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 1.7e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00062 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.07e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000456 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 6.73e-11 |\n", + "| loss_kl | 1.15e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.24e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000825 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 2.68e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00842 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.24e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00167 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 6.18e-11 |\n", + "| loss_kl | 5.27e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000383 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 3.76e-11 |\n", + "| loss_kl | 2.68e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 8.8e-11 |\n", + "| loss_kl | 2.57e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00284 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000174 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 8.76e-06 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00065 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.25e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00232 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 7.81e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00121 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 5.32e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00169 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 4.71e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.0135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.26e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00156 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 8.75e-11 |\n", + "| loss_kl | 5.47e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.00294 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.26e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000771 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 3.99e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00271 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.26e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00216 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 2.95e-10 |\n", + "| loss_kl | 4.78e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000237 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.55e+06 |\n", + "| TimeElapsed | 8.27e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000674 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00518 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.27e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000242 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 4.33e-11 |\n", + "| loss_kl | 7.99e-06 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00448 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.27e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 2.99e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00351 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.28e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000608 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 9.77e-11 |\n", + "| loss_kl | 2.66e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | 0.000914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000349 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 4.99e-11 |\n", + "| loss_kl | 8.64e-06 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.00306 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000249 |\n", + "| loss_pol_entpen | -0.486 |\n", + "| loss_vf_loss | 8.78e-11 |\n", + "| loss_kl | 1.11e-05 |\n", + "| loss_ent | 48.6 |\n", + "| ev_tdlam_before | -0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000434 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 2.8e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | 0.000225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 5.16e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.0316 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.29e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000331 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 1.78e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00684 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00117 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 6.26e-10 |\n", + "| loss_kl | 2.83e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | 0.000841 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.29e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000792 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 5.78e-10 |\n", + "| loss_kl | 3.83e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.042 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.3e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000908 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 2.02e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.0615 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.3e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000819 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 3.15e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00926 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.31e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 3.85e-10 |\n", + "| loss_kl | 3.75e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000605 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 5.03e-11 |\n", + "| loss_kl | 1.42e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.0015 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000404 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 3.79e-10 |\n", + "| loss_kl | 1.54e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | 8.64e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.31e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000234 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.08e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.31e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00188 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 5.98e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.32e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00135 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 6.42e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000714 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 3.03e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | 4.37e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.32e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00138 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 3.51e-10 |\n", + "| loss_kl | 3.92e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.32e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000286 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 2.05e-10 |\n", + "| loss_kl | 1.63e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.33e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.487 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 3.43e-05 |\n", + "| loss_ent | 48.7 |\n", + "| ev_tdlam_before | -0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.56e+06 |\n", + "| TimeElapsed | 8.33e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00212 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 4.92e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.0138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.33e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000726 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 3.62e-11 |\n", + "| loss_kl | 2.8e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.34e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0009 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 5.21e-10 |\n", + "| loss_kl | 3.37e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.00512 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 7.05e-11 |\n", + "| loss_kl | 6.03e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.0304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | 4.31e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | 9.63e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000759 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 3.26e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.00205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.34e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 3.74e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.000218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.94e-05 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 5.82e-11 |\n", + "| loss_kl | 5.84e-06 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.0192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000349 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 3.29e-10 |\n", + "| loss_kl | 8.29e-06 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | 0.000556 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.35e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000629 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 1.81e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.00936 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.36e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.488 |\n", + "| loss_vf_loss | 2.95e-11 |\n", + "| loss_kl | 2.6e-05 |\n", + "| loss_ent | 48.8 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00022 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.36e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 2.67e-10 |\n", + "| loss_kl | 5.01e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.000888 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000751 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.52e-11 |\n", + "| loss_kl | 3.97e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0413 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000164 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.61e-11 |\n", + "| loss_kl | 9.42e-06 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.000214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00295 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 7.52e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 7.11e-11 |\n", + "| loss_kl | 7.17e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 6.64e-11 |\n", + "| loss_kl | 3.46e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.57e+06 |\n", + "| TimeElapsed | 8.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000388 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.3e-10 |\n", + "| loss_kl | 1.89e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00187 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.38e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000483 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.45e-10 |\n", + "| loss_kl | 1.33e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 2.7e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00969 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.38e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000345 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 2.38e-10 |\n", + "| loss_kl | 1.3e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00434 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000266 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 6.58e-11 |\n", + "| loss_kl | 5.36e-06 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00744 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.39e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00071 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 2.07e-10 |\n", + "| loss_kl | 1.72e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00296 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.09e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.39e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 4.08e-10 |\n", + "| loss_kl | 3.54e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00771 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000276 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 9.25e-11 |\n", + "| loss_kl | 5.66e-06 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.0319 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00172 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 9.7e-11 |\n", + "| loss_kl | 3.74e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.001 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 6.94e-10 |\n", + "| loss_kl | 4.04e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.000103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00155 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.04e-11 |\n", + "| loss_kl | 4.14e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0816 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000865 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 3.94e-11 |\n", + "| loss_kl | 3.12e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0063 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.4e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000439 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 3.88e-11 |\n", + "| loss_kl | 1.54e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.00509 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.41e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000268 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 1.13e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.41e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 7.16e-11 |\n", + "| loss_kl | 4.1e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | -0.0215 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.41e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000247 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 5.02e-11 |\n", + "| loss_kl | 1.84e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.42e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000565 |\n", + "| loss_pol_entpen | -0.489 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 1.24e-05 |\n", + "| loss_ent | 48.9 |\n", + "| ev_tdlam_before | 0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.42e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 3.35e-10 |\n", + "| loss_kl | 5.23e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.000853 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00096 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.12e-09 |\n", + "| loss_kl | 2.89e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | 0.000905 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000397 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 2.36e-10 |\n", + "| loss_kl | 1.75e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000645 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 2.19e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | 0.000829 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00062 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 3.26e-10 |\n", + "| loss_kl | 1.39e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000324 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.58e+06 |\n", + "| TimeElapsed | 8.43e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00201 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 4.31e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00695 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.44e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 2.37e-11 |\n", + "| loss_kl | 3.88e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000155 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 6.79e-11 |\n", + "| loss_kl | 1.6e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00376 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000904 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 8.61e-11 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | 0.00257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.45e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 5.77e-11 |\n", + "| loss_kl | 3.1e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.45e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00118 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 9.01e-11 |\n", + "| loss_kl | 3.1e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00804 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.45e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000568 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 1.62e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00484 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.46e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000138 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 7.21e-06 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.000299 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000298 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 8.7e-06 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | 0.000648 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.46e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 9.95e-11 |\n", + "| loss_kl | 4.6e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.47e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000674 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 8.39e-11 |\n", + "| loss_kl | 4.01e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.000364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.47e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 8.71e-11 |\n", + "| loss_kl | 4.82e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | 0.00191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.1e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.47e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00185 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 5.1e-10 |\n", + "| loss_kl | 5.98e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00178 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 4.62e-10 |\n", + "| loss_kl | 5.02e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | 0.000737 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.48e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 4.05e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.000111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.48e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000656 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 7.17e-11 |\n", + "| loss_kl | 2.28e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.00558 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.48e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 3.64e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | 0.00964 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.59e+06 |\n", + "| TimeElapsed | 8.48e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00083 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 3.24e-10 |\n", + "| loss_kl | 3.3e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00952 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.49e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000613 |\n", + "| loss_pol_entpen | -0.49 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 2.19e-05 |\n", + "| loss_ent | 49 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.49e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 9.93e-11 |\n", + "| loss_kl | 2.67e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.0136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 6.66e-11 |\n", + "| loss_kl | 4.3e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00602 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 5.44e-06 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 9.78e-06 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.5e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00032 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 6.68e-06 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.0034 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.5e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000116 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 6.77e-11 |\n", + "| loss_kl | 1.93e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.000897 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000958 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 1.88e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | 0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00264 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 5.02e-11 |\n", + "| loss_kl | 6.78e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.017 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000951 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 4.94e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | 0.00197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000405 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00052 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000823 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 2.47e-10 |\n", + "| loss_kl | 3.02e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00714 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000929 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 8.62e-11 |\n", + "| loss_kl | 3.76e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.52e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000713 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 7.6e-11 |\n", + "| loss_kl | 1.74e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | 0.00102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.52e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000302 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 7.58e-11 |\n", + "| loss_kl | 1.13e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.000475 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000556 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 1.07e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000297 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 1.21e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.000937 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000975 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 2.03e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00099 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000737 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000566 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 2.69e-10 |\n", + "| loss_kl | 1.65e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.00954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000614 |\n", + "| loss_pol_entpen | -0.491 |\n", + "| loss_vf_loss | 4.95e-11 |\n", + "| loss_kl | 2.74e-05 |\n", + "| loss_ent | 49.1 |\n", + "| ev_tdlam_before | -0.0279 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 2.33e-10 |\n", + "| loss_kl | 3.09e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.00218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.54e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00234 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 5.21e-11 |\n", + "| loss_kl | 7.29e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.11e+03 |\n", + "| TimestepsSoFar | 1.6e+06 |\n", + "| TimeElapsed | 8.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000234 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 8.04e-11 |\n", + "| loss_kl | 1.88e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00863 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000266 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 7.33e-06 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.000552 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.56e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000941 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 2.24e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00382 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.56e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 2.13e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.56e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00202 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 3.16e-10 |\n", + "| loss_kl | 4.81e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.0203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.56e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00199 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 6.76e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00601 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.56e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00136 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 4.55e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.00396 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.57e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00141 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 4.18e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.0014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.57e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.44e-06 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 1.08e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000732 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 1.57e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000891 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 5.35e-10 |\n", + "| loss_kl | 2.57e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -1.9e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.58e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 9.21e-11 |\n", + "| loss_kl | 2.94e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00267 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.58e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000659 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 3.83e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00563 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000432 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 7.54e-11 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.00074 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.03e-10 |\n", + "| loss_kl | 3.19e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.00678 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00067 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 9.88e-11 |\n", + "| loss_kl | 2.4e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | -0.000933 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000325 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 1.31e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.0109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00203 |\n", + "| loss_pol_entpen | -0.492 |\n", + "| loss_vf_loss | 5.09e-11 |\n", + "| loss_kl | 4.35e-05 |\n", + "| loss_ent | 49.2 |\n", + "| ev_tdlam_before | 0.00265 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.61e+06 |\n", + "| TimeElapsed | 8.59e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 7.41e-10 |\n", + "| loss_kl | 2.91e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -3.45e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00092 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 3.83e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.0206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000735 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 5.39e-11 |\n", + "| loss_kl | 1.84e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | 0.00236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 9.59e-11 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.00282 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.61e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 8.4e-11 |\n", + "| loss_kl | 3.21e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.00175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000224 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.61e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0006 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 2.37e-10 |\n", + "| loss_kl | 1.75e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | 0.00967 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000911 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 7.27e-11 |\n", + "| loss_kl | 1.28e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.0535 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00089 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 3.21e-11 |\n", + "| loss_kl | 2.56e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.00541 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000594 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 3.93e-11 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.0121 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.58e-05 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 6.03e-11 |\n", + "| loss_kl | 4.59e-06 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | -0.000808 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000386 |\n", + "| loss_pol_entpen | -0.493 |\n", + "| loss_vf_loss | 8.38e-11 |\n", + "| loss_kl | 1.02e-05 |\n", + "| loss_ent | 49.3 |\n", + "| ev_tdlam_before | 0.00575 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.12e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 2.19e-10 |\n", + "| loss_kl | 2.27e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.00372 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00024 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 2.17e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | 0.00158 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00148 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 8.86e-11 |\n", + "| loss_kl | 3.15e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.0023 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.63e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00196 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 7.8e-11 |\n", + "| loss_kl | 5.89e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.00259 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 5.14e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.64e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0005 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 1.88e-10 |\n", + "| loss_kl | 1.78e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | 0.0236 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.64e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000276 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 1.66e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.00279 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0004 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 6.39e-11 |\n", + "| loss_kl | 9.18e-06 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.000405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000794 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 6.08e-11 |\n", + "| loss_kl | 1.9e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | -0.0185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.494 |\n", + "| loss_vf_loss | 7.55e-11 |\n", + "| loss_kl | 3.3e-05 |\n", + "| loss_ent | 49.4 |\n", + "| ev_tdlam_before | 8.63e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000238 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 7.14e-11 |\n", + "| loss_kl | 2.01e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.00637 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 6.14e-11 |\n", + "| loss_kl | 3.28e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.00571 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000215 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.62e+06 |\n", + "| TimeElapsed | 8.65e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00064 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 4.33e-11 |\n", + "| loss_kl | 1.82e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.0139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.66e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000776 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 4.65e-11 |\n", + "| loss_kl | 2.1e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.0148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.66e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000146 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 4.3e-11 |\n", + "| loss_kl | 7.09e-06 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -2.59e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.67e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 7.09e-11 |\n", + "| loss_kl | 2.15e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.00243 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00177 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 3.39e-11 |\n", + "| loss_kl | 6.03e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.0263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000212 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.67e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 7.95e-11 |\n", + "| loss_kl | 3.87e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.00262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00176 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 9.92e-11 |\n", + "| loss_kl | 4.53e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | 0.00377 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000875 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 3.92e-11 |\n", + "| loss_kl | 3.14e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.00982 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00021 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 6.64e-11 |\n", + "| loss_kl | 1.17e-05 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | 0.00305 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000231 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 2.45e-11 |\n", + "| loss_kl | 5.6e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.000343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000813 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 7.92e-11 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.000596 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.68e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.68e-05 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 6.02e-11 |\n", + "| loss_kl | 9.72e-06 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | 0.00317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000311 |\n", + "| loss_pol_entpen | -0.495 |\n", + "| loss_vf_loss | 6.01e-11 |\n", + "| loss_kl | 7.15e-06 |\n", + "| loss_ent | 49.5 |\n", + "| ev_tdlam_before | -0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0013 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 2.8e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -5.67e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.7e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000157 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 1.33e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.00343 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.7e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000359 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 4.52e-11 |\n", + "| loss_kl | 8.29e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0347 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.7e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00109 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 7.25e-11 |\n", + "| loss_kl | 2.67e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.000631 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.13e+03 |\n", + "| TimestepsSoFar | 1.63e+06 |\n", + "| TimeElapsed | 8.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00049 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.1e-09 |\n", + "| loss_kl | 1.36e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00198 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 5.06e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0026 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 4.33e-05 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 9.6e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.000442 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00277 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 5.27e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000814 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.62e-11 |\n", + "| loss_kl | 4.55e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.00855 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000486 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.4e-11 |\n", + "| loss_kl | 1.5e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000413 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 1.29e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.01 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.72e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000841 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.94e-11 |\n", + "| loss_kl | 2.04e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.73e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00091 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.03e-11 |\n", + "| loss_kl | 1.9e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.00878 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.73e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000367 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 8.4e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.000217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.73e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000559 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 1.39e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 3.28e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.73e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000392 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 7.45e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000113 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.37e-11 |\n", + "| loss_kl | 5.13e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000777 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.49e-11 |\n", + "| loss_kl | 1.82e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 3.45e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -9.08e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.74e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 2.49e-11 |\n", + "| loss_kl | 2.72e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0205 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000543 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 9.7e-11 |\n", + "| loss_kl | 1.32e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.00083 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000616 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 6.97e-11 |\n", + "| loss_kl | 1.6e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.000257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000564 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.01e-11 |\n", + "| loss_kl | 1.6e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00484 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.76e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000963 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 2.71e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.000959 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.76e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 3.08e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.76e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.84e-11 |\n", + "| loss_kl | 3.21e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.76e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000718 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 2.24e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00392 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.64e+06 |\n", + "| TimeElapsed | 8.76e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00061 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 1.07e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.000809 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000713 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 3.18e-10 |\n", + "| loss_kl | 2.18e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0217 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0008 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.49e-11 |\n", + "| loss_kl | 1.96e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0972 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.77e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00104 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 3.85e-11 |\n", + "| loss_kl | 3.22e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | -0.0202 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000369 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 5.3e-11 |\n", + "| loss_kl | 8.14e-06 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00461 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.77e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.496 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 2.05e-05 |\n", + "| loss_ent | 49.6 |\n", + "| ev_tdlam_before | 0.00166 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.14e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000569 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 5.77e-11 |\n", + "| loss_kl | 1.85e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | -3.62e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000398 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 4.4e-11 |\n", + "| loss_kl | 1.01e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | 0.00264 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00132 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 2.51e-11 |\n", + "| loss_kl | 2.6e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | -0.00935 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000534 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 2.48e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | -0.000915 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.79e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00182 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 4.04e-10 |\n", + "| loss_kl | 3.43e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | -0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.79e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000341 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | -0.00036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.8e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00112 |\n", + "| loss_pol_entpen | -0.497 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 2.2e-05 |\n", + "| loss_ent | 49.7 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.8e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 2.24e-10 |\n", + "| loss_kl | 3.58e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.8e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000829 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 7.87e-11 |\n", + "| loss_kl | 3.28e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0352 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000621 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 8.5e-11 |\n", + "| loss_kl | 1.84e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00802 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000712 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 2e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00182 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.65e+06 |\n", + "| TimeElapsed | 8.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000244 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 3.99e-06 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -1.06e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000498 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.0054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -7.12e-05 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 7.45e-06 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0004 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 9.24e-11 |\n", + "| loss_kl | 1.11e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000291 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 9.38e-11 |\n", + "| loss_kl | 1.05e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000515 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000713 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 1.69e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0019 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.82e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000472 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 2.53e-10 |\n", + "| loss_kl | 1.67e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 3.91e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.83e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0014 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 5.94e-11 |\n", + "| loss_kl | 2.19e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.83e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000471 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 1.95e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.000559 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000986 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000333 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 7.34e-11 |\n", + "| loss_kl | 1.11e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000848 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000603 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 9.9e-11 |\n", + "| loss_kl | 1.18e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00302 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000211 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000521 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 2.81e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000671 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 7.92e-11 |\n", + "| loss_kl | 1.13e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0137 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000286 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 9.45e-06 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.0317 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.85e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 1.98e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00872 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 4.23e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000877 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000213 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.15e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.85e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00078 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 3.68e-10 |\n", + "| loss_kl | 1.44e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000961 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000336 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 9.06e-11 |\n", + "| loss_kl | 1.28e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00779 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000563 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 1e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00917 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000149 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.74e-10 |\n", + "| loss_kl | 5.66e-06 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00196 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.87e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000621 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 2e-10 |\n", + "| loss_kl | 9.69e-06 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00026 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.87e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.91e-10 |\n", + "| loss_kl | 2.34e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00946 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.66e+06 |\n", + "| TimeElapsed | 8.87e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000585 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 7.63e-11 |\n", + "| loss_kl | 1.17e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00164 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 7.57e-11 |\n", + "| loss_kl | 3.57e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000498 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0015 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 5.72e-11 |\n", + "| loss_kl | 4.48e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00131 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 3.5e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.000141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00056 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 1.67e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000606 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 8.03e-11 |\n", + "| loss_kl | 1.14e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.0091 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000207 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.88e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00082 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 4.69e-11 |\n", + "| loss_kl | 1.69e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00933 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.89e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000425 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 5.32e-11 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.000297 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000668 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 1.43e-10 |\n", + "| loss_kl | 1.65e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -1.19e-07 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000561 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 3.28e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00535 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000511 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 3.78e-10 |\n", + "| loss_kl | 1.54e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | -0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000535 |\n", + "| loss_pol_entpen | -0.498 |\n", + "| loss_vf_loss | 4.6e-10 |\n", + "| loss_kl | 1.02e-05 |\n", + "| loss_ent | 49.8 |\n", + "| ev_tdlam_before | 0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000199 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000331 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 1.98e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00809 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000467 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 1.39e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000431 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 1.16e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00704 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000954 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.91e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000577 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 9.04e-11 |\n", + "| loss_kl | 1.7e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.0344 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000205 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.67e+06 |\n", + "| TimeElapsed | 8.91e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.00271 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 5.11e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.000393 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000465 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 7.15e-11 |\n", + "| loss_kl | 3.45e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.000613 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000799 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 2e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.000224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000835 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 7.89e-11 |\n", + "| loss_kl | 2.16e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.0154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000751 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 5.67e-10 |\n", + "| loss_kl | 2.39e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.68e-05 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 2.01e-10 |\n", + "| loss_kl | 6.14e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00651 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.16e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000747 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 1.42e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.0014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000653 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 6.32e-11 |\n", + "| loss_kl | 1.47e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 3.27e-06 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 8.56e-11 |\n", + "| loss_kl | 2.5e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00671 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000151 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | 3.07e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000552 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 7.26e-11 |\n", + "| loss_kl | 1.11e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.0242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00175 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 3.98e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.94e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00057 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 1.57e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00349 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.95e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000442 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 7.22e-11 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000368 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 4.65e-11 |\n", + "| loss_kl | 7.45e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.000484 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.96e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00159 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 3.64e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.000244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.96e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000998 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 2.84e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.0194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.96e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00247 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 5.48e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000987 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 5.38e-11 |\n", + "| loss_kl | 1.79e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.0114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.97e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000281 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 3.59e-11 |\n", + "| loss_kl | 5.07e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00561 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000779 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 4.72e-11 |\n", + "| loss_kl | 1.16e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000418 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 7.57e-11 |\n", + "| loss_kl | 1.19e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00307 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000664 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 6.59e-11 |\n", + "| loss_kl | 1.47e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.0094 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.68e+06 |\n", + "| TimeElapsed | 8.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000391 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 8.19e-11 |\n", + "| loss_kl | 1.07e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.000669 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.98e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00031 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 4.64e-11 |\n", + "| loss_kl | 6.08e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00541 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.99e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000519 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 8.4e-11 |\n", + "| loss_kl | 1.04e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00312 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000101 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 6.2e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000921 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 6.93e-11 |\n", + "| loss_kl | 1.17e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000561 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 9.25e-11 |\n", + "| loss_kl | 1.48e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00021 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 8.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000512 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 9.56e-11 |\n", + "| loss_kl | 7.21e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | -0.00373 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000336 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 8.77e-11 |\n", + "| loss_kl | 9.18e-06 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.000563 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000303 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 9.6e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.0083 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000672 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 6.7e-11 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000921 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 2.1e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000753 |\n", + "| loss_pol_entpen | -0.499 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 1.04e-05 |\n", + "| loss_ent | 49.9 |\n", + "| ev_tdlam_before | 4.54e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.17e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.01e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000859 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 2.22e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0422 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.01e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000266 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.05e-11 |\n", + "| loss_kl | 7.84e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.02e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00133 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 2.57e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 7.21e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.02e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000635 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 9.42e-11 |\n", + "| loss_kl | 1.98e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.02e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000287 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 6.31e-11 |\n", + "| loss_kl | 3.34e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.000865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.02e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00128 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 8.63e-11 |\n", + "| loss_kl | 2.74e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00969 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000209 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.69e+06 |\n", + "| TimeElapsed | 9.02e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000413 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 1.69e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000177 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.33e-10 |\n", + "| loss_kl | 5.96e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00113 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 4.22e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.000108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000446 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 9e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00774 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.03e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000695 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 3.5e-10 |\n", + "| loss_kl | 1.42e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.00413 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.04e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000132 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | 7.39e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000497 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 1.01e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000733 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00332 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000928 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 2.24e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00856 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00034 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 6.78e-11 |\n", + "| loss_kl | 1.16e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 8.6e-11 |\n", + "| loss_kl | 1.34e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000216 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.05e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00103 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 2.06e-10 |\n", + "| loss_kl | 1.97e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.06e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 4.27e-10 |\n", + "| loss_kl | 2.54e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.06e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000658 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.57e-10 |\n", + "| loss_kl | 1.45e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0437 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.06e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00045 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 8.52e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.0124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.06e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000463 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 7.29e-11 |\n", + "| loss_kl | 9.95e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.00218 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.07e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000432 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 5.94e-11 |\n", + "| loss_kl | 1.15e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.000323 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000217 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.07e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000249 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 7.09e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -4.58e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000432 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 8.51e-11 |\n", + "| loss_kl | 7.81e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000338 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 4.44e-11 |\n", + "| loss_kl | 5.78e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00436 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000579 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 5.52e-11 |\n", + "| loss_kl | 1.04e-05 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | 0.000242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.53e-05 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 2.21e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -2.62e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00046 |\n", + "| loss_pol_entpen | -0.5 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 5.72e-06 |\n", + "| loss_ent | 50 |\n", + "| ev_tdlam_before | -0.000728 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000219 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.18e+03 |\n", + "| TimestepsSoFar | 1.7e+06 |\n", + "| TimeElapsed | 9.08e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000107 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 3.4e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 5.09e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.09e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000161 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 3.34e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00653 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.09e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000462 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 8.4e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.09e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 8.71e-11 |\n", + "| loss_kl | 2.3e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00731 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.1e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 7.15e-11 |\n", + "| loss_kl | 2.68e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.1e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000769 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.5e-10 |\n", + "| loss_kl | 1.44e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000821 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000268 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 8.29e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000781 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 5.5e-11 |\n", + "| loss_kl | 1.82e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000544 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00126 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 2.81e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.000891 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.96e-05 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 9.72e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000825 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000313 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 6.62e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000362 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.11e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000432 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 1.41e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000902 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.12e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000366 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 8.58e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.0127 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.12e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 3.71e-10 |\n", + "| loss_kl | 1.88e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 1.19e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.12e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.93e-05 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 2.68e-10 |\n", + "| loss_kl | 2.56e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0404 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.13e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000226 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 3.99e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00943 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.13e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000233 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 3.44e-11 |\n", + "| loss_kl | 4.83e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.71e+06 |\n", + "| TimeElapsed | 9.13e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000939 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 7.38e-11 |\n", + "| loss_kl | 2.08e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000404 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 4.94e-11 |\n", + "| loss_kl | 1.44e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.000501 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00021 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 4.35e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00484 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000711 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 1.13e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000659 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 5.87e-11 |\n", + "| loss_kl | 1.15e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.000326 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000628 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 2.19e-10 |\n", + "| loss_kl | 1.23e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.14e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000446 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 9.72e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000805 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 3.97e-11 |\n", + "| loss_kl | 1.19e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00999 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.15e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000664 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 9.9e-11 |\n", + "| loss_kl | 1.45e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.16e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00026 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 3.47e-11 |\n", + "| loss_kl | 5.78e-06 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.16e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 6.93e-11 |\n", + "| loss_kl | 2.32e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00023 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.19e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.16e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000644 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 3.12e-10 |\n", + "| loss_kl | 1.36e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000535 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000948 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 1.93e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00106 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 2e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.0199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.0012 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 5.29e-11 |\n", + "| loss_kl | 2.63e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.00985 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 4.66e-11 |\n", + "| loss_kl | 3.09e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00192 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000834 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 8.41e-11 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | 0.000708 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.72e+06 |\n", + "| TimeElapsed | 9.17e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.501 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 2.76e-05 |\n", + "| loss_ent | 50.1 |\n", + "| ev_tdlam_before | -0.00532 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.18e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00093 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 2.62e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -8.07e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.18e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000656 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 1.7e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.000672 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.19e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00166 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 6.94e-11 |\n", + "| loss_kl | 3.18e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000345 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.92e-10 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.19e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00102 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 8.51e-11 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00622 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000231 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.19e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000228 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 5.01e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000537 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 7.6e-11 |\n", + "| loss_kl | 1.06e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.59e-05 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 7.01e-11 |\n", + "| loss_kl | 4.29e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000751 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 3.87e-11 |\n", + "| loss_kl | 1.34e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00271 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000568 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 1.39e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000237 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.26e-10 |\n", + "| loss_kl | 4.53e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.2e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000208 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.93e-10 |\n", + "| loss_kl | 9.83e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00479 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.21e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000412 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 5.3e-11 |\n", + "| loss_kl | 9.36e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.008 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.22e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000464 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 5.79e-10 |\n", + "| loss_kl | 8.76e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.000262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.22e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000853 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 9.36e-11 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -4.53e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.22e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000917 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.02e-10 |\n", + "| loss_kl | 1.62e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.22e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000791 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 3.53e-11 |\n", + "| loss_kl | 1.28e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00522 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00104 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 4.04e-10 |\n", + "| loss_kl | 2.11e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -1.07e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000448 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 9.83e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00266 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.000528 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.23e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000952 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 2.53e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.23e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00039 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 9.64e-11 |\n", + "| loss_kl | 5.96e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.2e+03 |\n", + "| TimestepsSoFar | 1.73e+06 |\n", + "| TimeElapsed | 9.24e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00129 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 2.83e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00076 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.24e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.69e-05 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 9.13e-11 |\n", + "| loss_kl | 2.38e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.24e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00123 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 6.54e-11 |\n", + "| loss_kl | 1.57e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00544 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000793 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 8.09e-11 |\n", + "| loss_kl | 1.57e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00564 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.25e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00173 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 6.77e-11 |\n", + "| loss_kl | 3.4e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.25e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00062 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 3.2e-10 |\n", + "| loss_kl | 2.39e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00261 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000225 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.25e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000668 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.34e-10 |\n", + "| loss_kl | 1.39e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.000954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.26e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 9.01e-11 |\n", + "| loss_kl | 1.74e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.26e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000806 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 7.44e-11 |\n", + "| loss_kl | 1.98e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0088 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.26e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000477 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.26e-10 |\n", + "| loss_kl | 1.21e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.26e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000563 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 6.38e-11 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.0142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.26e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00028 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 5.53e-11 |\n", + "| loss_kl | 3.99e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000229 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.27e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000501 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 8.61e-11 |\n", + "| loss_kl | 5.19e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -1.44e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.27e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000616 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 1.37e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000156 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.32e-10 |\n", + "| loss_kl | 5.22e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00332 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000922 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 1.53e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.000794 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000668 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.77e-10 |\n", + "| loss_kl | 1.28e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | 0.00877 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.74e+06 |\n", + "| TimeElapsed | 9.28e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000733 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.08e-11 |\n", + "| loss_kl | 9.89e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000686 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.29e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000874 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 8.42e-11 |\n", + "| loss_kl | 1.92e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00486 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.29e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000321 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.88e-11 |\n", + "| loss_kl | 9.69e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00173 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.29e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000479 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.55e-11 |\n", + "| loss_kl | 7.87e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00246 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.29e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00064 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 8.76e-11 |\n", + "| loss_kl | 1.31e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000341 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.3e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000459 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.84e-11 |\n", + "| loss_kl | 4.29e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000232 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.3e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000597 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.68e-11 |\n", + "| loss_kl | 7.15e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00285 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.3e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00111 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 5.87e-11 |\n", + "| loss_kl | 2.25e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.000443 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000508 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 1.32e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000261 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 4.8e-11 |\n", + "| loss_kl | 5.01e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.31e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000201 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.31e-11 |\n", + "| loss_kl | 4.53e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.31e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00057 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 7.48e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0037 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.21e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.31e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000346 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 6.08e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00283 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.32e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000498 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 6.79e-11 |\n", + "| loss_kl | 8.29e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.000826 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.32e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000186 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 3.46e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00338 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.32e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000457 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.43e-11 |\n", + "| loss_kl | 6.62e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00455 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.32e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000544 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 9.12e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0033 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.33e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000224 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.94e-10 |\n", + "| loss_kl | 4.56e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -9.07e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000222 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.33e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000713 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.34e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000846 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 1.87e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.34e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00145 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 2.65e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.34e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00101 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 2.59e-05 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.00732 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.34e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000322 |\n", + "| loss_pol_entpen | -0.502 |\n", + "| loss_vf_loss | 3.1e-11 |\n", + "| loss_kl | 9.12e-06 |\n", + "| loss_ent | 50.2 |\n", + "| ev_tdlam_before | -0.0809 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000227 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.75e+06 |\n", + "| TimeElapsed | 9.34e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000554 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 6.28e-10 |\n", + "| loss_kl | 1.08e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000577 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 3.43e-10 |\n", + "| loss_kl | 1.1e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00463 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.35e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000491 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.39e-10 |\n", + "| loss_kl | 1.21e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.35e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0011 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 5.13e-10 |\n", + "| loss_kl | 1.53e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00537 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.35e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 6.96e-05 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 2.92e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00746 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.36e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000521 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 6.79e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00402 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000223 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.36e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000814 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 1.44e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.000195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000805 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000796 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 3.58e-10 |\n", + "| loss_kl | 1.66e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000694 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 1.25e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0943 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000297 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 4.52e-10 |\n", + "| loss_kl | 5.9e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000481 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00144 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 2.31e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.0131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000221 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.37e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000361 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.3e-11 |\n", + "| loss_kl | 3.46e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 7.23e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00115 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 4.56e-11 |\n", + "| loss_kl | 2e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000928 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.38e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000475 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.59e-11 |\n", + "| loss_kl | 1.31e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0117 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.38e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00063 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 8.72e-11 |\n", + "| loss_kl | 5.54e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000717 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.38e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000772 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 7.3e-11 |\n", + "| loss_kl | 1.51e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000436 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.12e-11 |\n", + "| loss_kl | 1.04e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.00139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000226 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.22e+03 |\n", + "| TimestepsSoFar | 1.76e+06 |\n", + "| TimeElapsed | 9.39e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000377 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.74e-10 |\n", + "| loss_kl | 5.6e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00036 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.4e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00108 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.65e-10 |\n", + "| loss_kl | 1.85e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00272 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.4e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000162 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | 6.5e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.4e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000433 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 8.05e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.4e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000724 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 7.75e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.0061 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.4e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000934 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.64e-10 |\n", + "| loss_kl | 1.38e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000225 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.41e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000146 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.41e-10 |\n", + "| loss_kl | 4.89e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.41e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000439 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 9.65e-11 |\n", + "| loss_kl | 6.44e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.41e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00076 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 1.24e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000836 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.42e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000459 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 8.91e-10 |\n", + "| loss_kl | 1.06e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00096 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.42e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00105 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 1.49e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.42e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00064 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 1.17e-05 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | 0.000114 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000323 |\n", + "| loss_pol_entpen | -0.503 |\n", + "| loss_vf_loss | 8.22e-11 |\n", + "| loss_kl | 8.46e-06 |\n", + "| loss_ent | 50.3 |\n", + "| ev_tdlam_before | -0.0116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000695 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 1.29e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000222 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 2.11e-10 |\n", + "| loss_kl | 7.99e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000183 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 2.83e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000501 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000821 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 7.47e-11 |\n", + "| loss_kl | 1.22e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 6.36e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000247 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.43e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.77e-05 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 5.56e-11 |\n", + "| loss_kl | 1.79e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.00242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.44e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000738 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 8e-11 |\n", + "| loss_kl | 9.48e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000162 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.44e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 3.33e-11 |\n", + "| loss_kl | 1.17e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.0063 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.44e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000135 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 7.92e-11 |\n", + "| loss_kl | 3.99e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.00382 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000265 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.09e-10 |\n", + "| loss_kl | 4.71e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.0013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000747 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 3.15e-11 |\n", + "| loss_kl | 1.01e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.00409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000244 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.77e+06 |\n", + "| TimeElapsed | 9.45e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000197 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 6.11e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 4.26e-11 |\n", + "| loss_kl | 9.42e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.000888 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000782 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 9.89e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.000339 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000593 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 1.34e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.00436 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000223 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 2.71e-11 |\n", + "| loss_kl | 6.68e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000687 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.23e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.46e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000731 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 6.33e-11 |\n", + "| loss_kl | 1.19e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 0.0141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.47e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000355 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 5.85e-11 |\n", + "| loss_kl | 9.54e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00633 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.48e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000625 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 9.74e-11 |\n", + "| loss_kl | 1.13e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000469 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.48e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000576 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 3.96e-11 |\n", + "| loss_kl | 1.12e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.0043 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.48e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000839 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 3.22e-11 |\n", + "| loss_kl | 1.45e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00248 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.48e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000247 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 8.51e-11 |\n", + "| loss_kl | 5.07e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000778 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000243 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.48e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000489 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 3.77e-11 |\n", + "| loss_kl | 1.1e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00142 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.49e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00107 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 1.35e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.49e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000138 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 2.91e-10 |\n", + "| loss_kl | 3.34e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00635 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.49e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000882 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 1.23e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000191 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.49e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000599 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 1.09e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.49e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000425 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 8.88e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00109 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.78e+06 |\n", + "| TimeElapsed | 9.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000437 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 5.6e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | 7.46e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.5e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000828 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 2.35e-10 |\n", + "| loss_kl | 1.15e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00865 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000441 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.81e-10 |\n", + "| loss_kl | 1.04e-05 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000942 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000676 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 9.78e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.00124 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.51e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00016 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 5.19e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.0018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.51e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000593 |\n", + "| loss_pol_entpen | -0.504 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 8.11e-06 |\n", + "| loss_ent | 50.4 |\n", + "| ev_tdlam_before | -0.000718 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000239 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.51e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00147 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.46e-11 |\n", + "| loss_kl | 2.41e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000841 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.52e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | 8.44e-05 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.81e-11 |\n", + "| loss_kl | 3.04e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000663 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.52e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000604 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.96e-10 |\n", + "| loss_kl | 7.69e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00235 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.52e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000322 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 7.63e-11 |\n", + "| loss_kl | 7.69e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0303 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.52e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000565 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.36e-11 |\n", + "| loss_kl | 7.45e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000201 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000235 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.53e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000537 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.1e-11 |\n", + "| loss_kl | 9.06e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00016 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 5.19e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00478 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000663 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 9.48e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00301 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00036 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.71e-10 |\n", + "| loss_kl | 4.29e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 7.83e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000189 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.07e-10 |\n", + "| loss_kl | 4.68e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000313 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 3.64e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 2.56e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000236 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.24e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.54e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000148 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 3.75e-10 |\n", + "| loss_kl | 1.61e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000104 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 9.55e-11 |\n", + "| loss_kl | 2.09e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.0125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000161 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.6e-10 |\n", + "| loss_kl | 1.91e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00849 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000856 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.67e-10 |\n", + "| loss_kl | 1.07e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00264 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.55e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000342 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.01e-10 |\n", + "| loss_kl | 9.18e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00714 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.56e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000564 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.87e-10 |\n", + "| loss_kl | 6.97e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00817 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.79e+06 |\n", + "| TimeElapsed | 9.56e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000507 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 9.05e-11 |\n", + "| loss_kl | 6.5e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000308 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 4.47e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00759 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000324 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.2e-10 |\n", + "| loss_kl | 7.27e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00361 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000362 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.29e-11 |\n", + "| loss_kl | 5.04e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000963 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000262 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.65e-11 |\n", + "| loss_kl | 3.64e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000398 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.55e-11 |\n", + "| loss_kl | 6.08e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00736 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000228 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.57e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000963 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2e-10 |\n", + "| loss_kl | 1.56e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.58e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000374 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.22e-10 |\n", + "| loss_kl | 7.39e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00255 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.58e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00044 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 4.89e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.58e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000249 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.03e-11 |\n", + "| loss_kl | 2.68e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00416 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000174 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.1e-10 |\n", + "| loss_kl | 4.71e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00523 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000233 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.59e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000377 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 9.65e-11 |\n", + "| loss_kl | 3.52e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00228 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0003 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.89e-10 |\n", + "| loss_kl | 4.71e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000227 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.03e-10 |\n", + "| loss_kl | 2.38e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000195 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000478 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.15e-10 |\n", + "| loss_kl | 6.2e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000268 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.49e-11 |\n", + "| loss_kl | 5.66e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0458 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.96e-11 |\n", + "| loss_kl | 2.26e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000584 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000238 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.8e+06 |\n", + "| TimeElapsed | 9.6e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000261 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 4.17e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00325 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.61e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000301 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.51e-10 |\n", + "| loss_kl | 4.62e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.61e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000854 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.62e-10 |\n", + "| loss_kl | 9.95e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.61e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000209 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 6.44e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000908 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000746 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 7.99e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.62e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000356 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.79e-10 |\n", + "| loss_kl | 7.48e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00779 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00024 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.25e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.62e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0002 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 7.22e-11 |\n", + "| loss_kl | 5.13e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0081 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000373 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.56e-11 |\n", + "| loss_kl | 4.65e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000466 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.49e-11 |\n", + "| loss_kl | 7.57e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000759 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000716 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 8.37e-11 |\n", + "| loss_kl | 8.34e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000314 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.42e-11 |\n", + "| loss_kl | 4.89e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.039 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000507 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.12e-11 |\n", + "| loss_kl | 5.66e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0016 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000242 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.63e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000399 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.31e-11 |\n", + "| loss_kl | 4.35e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00844 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.64e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000257 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 2.86e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00274 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.64e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000268 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.32e-11 |\n", + "| loss_kl | 4.35e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.65e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000634 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 3.49e-11 |\n", + "| loss_kl | 8.55e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0054 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.65e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000442 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.91e-11 |\n", + "| loss_kl | 6.97e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000253 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.65e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00114 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.69e-11 |\n", + "| loss_kl | 1.73e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00464 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000422 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.96e-11 |\n", + "| loss_kl | 4.17e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000661 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000666 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 8.94e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000294 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000675 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 4.96e-11 |\n", + "| loss_kl | 1.16e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000186 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 7.58e-11 |\n", + "| loss_kl | 2.38e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000382 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 3.5e-11 |\n", + "| loss_kl | 3.73e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00995 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000259 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.81e+06 |\n", + "| TimeElapsed | 9.66e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000226 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.82e-10 |\n", + "| loss_kl | 3.22e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.67e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000409 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.3e-11 |\n", + "| loss_kl | 5.6e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00123 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.67e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00021 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.14e-10 |\n", + "| loss_kl | 1.88e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.68e+03 |\n", + "------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -4.11e-05 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 9.57e-11 |\n", + "| loss_kl | 1.85e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.68e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000328 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | 3.28e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000625 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.68e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000498 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 7.37e-11 |\n", + "| loss_kl | 5.36e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.0112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.68e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00127 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 9.4e-11 |\n", + "| loss_kl | 1.69e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.66e-10 |\n", + "| loss_kl | 5.13e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000261 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.24e-10 |\n", + "| loss_kl | 2.8e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000198 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.94e-11 |\n", + "| loss_kl | 3.04e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00136 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000926 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.18e-10 |\n", + "| loss_kl | 1.14e-05 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000183 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000106 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.73e-11 |\n", + "| loss_kl | 3.76e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.26e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.69e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000781 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 7.63e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00243 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.7e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000927 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 6.99e-11 |\n", + "| loss_kl | 9.72e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.000813 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.7e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00022 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.15e-10 |\n", + "| loss_kl | 1.55e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00837 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.71e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000234 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.83e-10 |\n", + "| loss_kl | 2.44e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000899 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 8.88e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.0111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.82e+06 |\n", + "| TimeElapsed | 9.71e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000433 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.81e-11 |\n", + "| loss_kl | 4.11e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00322 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.72e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000877 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 8.91e-11 |\n", + "| loss_kl | 1.09e-05 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.000674 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.72e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000214 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 2.99e-11 |\n", + "| loss_kl | 5.16e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.72e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000426 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 4.71e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | 0.00018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.72e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000655 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 8.38e-11 |\n", + "| loss_kl | 8.64e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.0103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.72e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "------------------------------\n", + "| loss_pol_surr | -0.00044 |\n", + "| loss_pol_entpen | -0.505 |\n", + "| loss_vf_loss | 5.17e-11 |\n", + "| loss_kl | 6.44e-06 |\n", + "| loss_ent | 50.5 |\n", + "| ev_tdlam_before | -0.00239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.73e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000443 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.3e-11 |\n", + "| loss_kl | 5.19e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000838 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.73e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.001 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.07e-11 |\n", + "| loss_kl | 1.26e-05 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00125 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.74e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.07e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.41e-10 |\n", + "| loss_kl | 2.5e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -6.5e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000285 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.23e-11 |\n", + "| loss_kl | 4.17e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0216 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000834 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.56e-11 |\n", + "| loss_kl | 8.26e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000322 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 5.42e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00838 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000262 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.74e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000149 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.82e-10 |\n", + "| loss_kl | 2.09e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.0057 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000293 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 3.28e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0182 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000162 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5e-11 |\n", + "| loss_kl | 1.91e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00288 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.75e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000549 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.83e-11 |\n", + "| loss_kl | 4.41e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.75e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00032 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 5.01e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.75e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000136 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 2.26e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.0131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000268 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.76e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000265 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.81e-11 |\n", + "| loss_kl | 4.05e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00262 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.76e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000469 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.52e-11 |\n", + "| loss_kl | 6.68e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.77e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00058 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.57e-11 |\n", + "| loss_kl | 7.27e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00643 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.77e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000346 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.32e-11 |\n", + "| loss_kl | 5.78e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.0047 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.77e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000536 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.44e-11 |\n", + "| loss_kl | 7.57e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 2.04e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.27e+03 |\n", + "| TimestepsSoFar | 1.83e+06 |\n", + "| TimeElapsed | 9.77e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.56e-11 |\n", + "| loss_kl | 2.09e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -8.34e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.78e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000631 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.16e-10 |\n", + "| loss_kl | 5.42e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000371 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.49e-10 |\n", + "| loss_kl | 5.54e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00051 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000204 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 2.15e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000138 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.78e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000255 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.54e-10 |\n", + "| loss_kl | 2.44e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00562 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.46e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 1.19e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00742 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000191 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 8e-11 |\n", + "| loss_kl | 3.93e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00101 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.79e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000324 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.8e-11 |\n", + "| loss_kl | 4.59e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.53e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.83e-11 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00157 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000118 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.95e-11 |\n", + "| loss_kl | 1.49e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000736 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.1e-11 |\n", + "| loss_kl | 6.26e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00047 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000772 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.97e-11 |\n", + "| loss_kl | 1.01e-05 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00172 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.8e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000336 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 3.64e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000386 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.35e-11 |\n", + "| loss_kl | 4.83e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00603 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000373 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.47e-10 |\n", + "| loss_kl | 3.58e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000252 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000274 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.02e-10 |\n", + "| loss_kl | 4.41e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00757 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.81e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000474 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.28e-11 |\n", + "| loss_kl | 5.78e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00139 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.82e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000812 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.95e-11 |\n", + "| loss_kl | 6.85e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00412 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.84e+06 |\n", + "| TimeElapsed | 9.82e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000349 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 3.04e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00552 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000241 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.25e-10 |\n", + "| loss_kl | 2.68e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000299 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.83e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000288 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.35e-10 |\n", + "| loss_kl | 4.17e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00889 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000163 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.5e-11 |\n", + "| loss_kl | 2.8e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000139 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.63e-11 |\n", + "| loss_kl | 1.85e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0212 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000277 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.83e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000249 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.94e-11 |\n", + "| loss_kl | 1.34e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00772 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00033 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.39e-11 |\n", + "| loss_kl | 3.81e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000238 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000388 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 8.45e-11 |\n", + "| loss_kl | 5.13e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.84e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000178 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.2e-11 |\n", + "| loss_kl | 1.91e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0151 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000327 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.11e-11 |\n", + "| loss_kl | 3.1e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000146 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.17e-11 |\n", + "| loss_kl | 3.7e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0219 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.28e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.85e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.02e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.63e-10 |\n", + "| loss_kl | 8.05e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000116 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.93e-11 |\n", + "| loss_kl | 1.4e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00275 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000953 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.16e-11 |\n", + "| loss_kl | 6.79e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00135 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00055 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6e-11 |\n", + "| loss_kl | 9.12e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000392 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.52e-11 |\n", + "| loss_kl | 5.3e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00385 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000188 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.47e-11 |\n", + "| loss_kl | 1.61e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.86e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.19e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 4.47e-11 |\n", + "| loss_kl | 1.67e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.018 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.87e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000338 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.01e-10 |\n", + "| loss_kl | 2.92e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -9.45e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.87e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000614 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.35e-11 |\n", + "| loss_kl | 5.42e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000734 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.87e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000157 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.3e-11 |\n", + "| loss_kl | 1.67e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00258 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.87e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -7.57e-06 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000823 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.88e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000404 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.79e-11 |\n", + "| loss_kl | 3.37e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00249 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.85e+06 |\n", + "| TimeElapsed | 9.88e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000415 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.5e-10 |\n", + "| loss_kl | 3.25e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00648 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000229 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.39e-10 |\n", + "| loss_kl | 3.58e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00171 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000351 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.5e-11 |\n", + "| loss_kl | 2.98e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0105 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000153 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.93e-10 |\n", + "| loss_kl | 2.5e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.87e-10 |\n", + "| loss_kl | 1.43e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000278 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.89e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000117 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.57e-11 |\n", + "| loss_kl | 1.25e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000232 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.9e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000359 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.71e-11 |\n", + "| loss_kl | 2.98e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00239 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.9e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00019 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.46e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00233 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.9e+03 |\n", + "------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00024 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.52e-11 |\n", + "| loss_kl | 2.74e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00687 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000451 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.37e-11 |\n", + "| loss_kl | 3.52e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00611 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.91e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0003 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 3.93e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.91e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000217 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.25e-10 |\n", + "| loss_kl | 1.97e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.61e-05 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000412 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00035 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.13e-10 |\n", + "| loss_kl | 2.47e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000581 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000308 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 3.34e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00116 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000257 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.45e-11 |\n", + "| loss_kl | 2.68e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00573 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000202 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 8e-11 |\n", + "| loss_kl | 2.38e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00203 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.29e+03 |\n", + "| TimestepsSoFar | 1.86e+06 |\n", + "| TimeElapsed | 9.92e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.16e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.000518 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000331 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 6.54e-11 |\n", + "| loss_kl | 2.32e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 0.00887 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000291 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.05e-11 |\n", + "| loss_kl | 3.81e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00141 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.93e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000226 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.09e-10 |\n", + "| loss_kl | 2.68e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000206 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00037 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.79e-10 |\n", + "| loss_kl | 3.1e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000737 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000172 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 2.26e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00351 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.94e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000308 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 2.17e-10 |\n", + "| loss_kl | 2.21e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000291 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.73e-10 |\n", + "| loss_kl | 2.86e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00972 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000353 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 3.4e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00198 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000339 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 3.04e-10 |\n", + "| loss_kl | 3.46e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000811 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.95e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000155 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 5.79e-11 |\n", + "| loss_kl | 6.26e-07 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000293 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.95e+03 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00022 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 1.85e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00386 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.96e+03 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000244 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 1.85e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.00852 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.96e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000452 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 7.19e-11 |\n", + "| loss_kl | 3.22e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | 8.09e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000539 |\n", + "| loss_pol_entpen | -0.506 |\n", + "| loss_vf_loss | 9.49e-11 |\n", + "| loss_kl | 5.9e-06 |\n", + "| loss_ent | 50.6 |\n", + "| ev_tdlam_before | -0.000331 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000317 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 4.05e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000363 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 4.47e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.97e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000534 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.65e-11 |\n", + "| loss_kl | 4.35e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00204 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.95e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.22e-11 |\n", + "| loss_kl | 1.79e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000444 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.04e-11 |\n", + "| loss_kl | 3.19e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00251 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000168 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.76e-10 |\n", + "| loss_kl | 3.01e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000852 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000667 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 5.87e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00379 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000103 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 3.69e-11 |\n", + "| loss_kl | 2.92e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00875 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.87e+06 |\n", + "| TimeElapsed | 9.98e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.87e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.13e-11 |\n", + "| loss_kl | 9.54e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 9.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000352 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.32e-11 |\n", + "| loss_kl | 3.1e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 9.99e+03 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000469 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.06e-11 |\n", + "| loss_kl | 4.53e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.005 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.78e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 1.19e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000487 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000509 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 2.04e-10 |\n", + "| loss_kl | 3.87e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00431 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000105 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.64e-10 |\n", + "| loss_kl | 1.97e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00134 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.3e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000292 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 4.29e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000257 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00021 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.23e-11 |\n", + "| loss_kl | 2.38e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.0149 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.16e-11 |\n", + "| loss_kl | 1.49e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00143 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000522 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 2.07e-10 |\n", + "| loss_kl | 4.05e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000187 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.56e-11 |\n", + "| loss_kl | 1.91e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00947 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000288 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000121 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.63e-11 |\n", + "| loss_kl | 3.16e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000476 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 3.74e-11 |\n", + "| loss_kl | 3.58e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000256 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 2.32e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000237 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000336 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 9.27e-11 |\n", + "| loss_kl | 3.28e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00508 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000384 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.97e-11 |\n", + "| loss_kl | 3.81e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.0156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.89e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.99e-10 |\n", + "| loss_kl | 8.94e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -1.79e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000283 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.88e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.77e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 1.61e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000647 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.25e-11 |\n", + "| loss_kl | 1.16e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000369 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.38e-11 |\n", + "| loss_kl | 2.77e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0174 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000514 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 3.64e-11 |\n", + "| loss_kl | 4.77e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000208 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.13e-11 |\n", + "| loss_kl | 2.32e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000358 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.73e-11 |\n", + "| loss_kl | 1.79e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000753 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000282 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000106 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.55e-10 |\n", + "| loss_kl | 9.54e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0061 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000351 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.61e-11 |\n", + "| loss_kl | 1.61e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -9.54e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00025 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.98e-11 |\n", + "| loss_kl | 2.18e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.0106 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000549 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.03e-11 |\n", + "| loss_kl | 4.11e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00178 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.18e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.07e-11 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00831 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000227 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.44e-11 |\n", + "| loss_kl | 1.43e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00266 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000291 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000259 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.2e-10 |\n", + "| loss_kl | 1.97e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00381 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.95e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 9.51e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00445 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000404 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.51e-11 |\n", + "| loss_kl | 2.83e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00417 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00023 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.07e-11 |\n", + "| loss_kl | 1.67e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -7.4e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000376 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 2.26e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.31e+03 |\n", + "| TimestepsSoFar | 1.89e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000119 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.95e-10 |\n", + "| loss_kl | 8.34e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000213 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000162 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000773 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000202 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 9.4e-11 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00726 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000184 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.42e-10 |\n", + "| loss_kl | 1.28e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00113 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.65e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.34e-10 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00367 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000218 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.62e-11 |\n", + "| loss_kl | 1.25e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.0197 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000156 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.71e-11 |\n", + "| loss_kl | 1.13e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00245 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000151 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.7e-10 |\n", + "| loss_kl | 1.28e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00454 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000156 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 2.27e-10 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0041 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 2.08e-10 |\n", + "| loss_kl | 1.31e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00542 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.22e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00223 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000522 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.84e-10 |\n", + "| loss_kl | 3.46e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00037 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000298 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000148 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | 2.03e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00466 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000108 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.74e-11 |\n", + "| loss_kl | 8.34e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0013 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000105 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.77e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000593 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000233 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.72e-10 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000433 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.85e-11 |\n", + "| loss_kl | 2.56e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00396 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.11e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.78e-10 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0014 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000228 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.84e-11 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000247 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -9.65e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 6.85e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00126 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000253 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.08e-11 |\n", + "| loss_kl | 1.28e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000626 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000231 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 9.94e-11 |\n", + "| loss_kl | 1.55e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00347 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000225 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.58e-10 |\n", + "| loss_kl | 1.73e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00215 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.9e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000331 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.36e-11 |\n", + "| loss_kl | 1.79e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000387 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.45e-10 |\n", + "| loss_kl | 2.15e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000181 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 3.92e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.01e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000228 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 6.4e-11 |\n", + "| loss_kl | 1.67e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000906 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000213 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.08e-11 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000458 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 4.57e-11 |\n", + "| loss_kl | 2.92e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00522 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000299 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.32e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000126 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 1.49e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000193 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.69e-10 |\n", + "| loss_kl | 1.31e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00335 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.94e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.5e-11 |\n", + "| loss_kl | 6.26e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.55e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -2.54e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000235 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.64e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 5.32e-11 |\n", + "| loss_kl | 8.94e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00381 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000301 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00022 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 1.19e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000171 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.87e-11 |\n", + "| loss_kl | 1.4e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00168 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000417 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.53e-11 |\n", + "| loss_kl | 2.44e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0028 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -7.35e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00556 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00036 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 1.97e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00799 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000191 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.4e-11 |\n", + "| loss_kl | 8.94e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00854 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000303 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.91e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000157 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.19e-11 |\n", + "| loss_kl | 1.91e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00209 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.18e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 8.12e-11 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00319 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000171 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 7.82e-11 |\n", + "| loss_kl | 1.19e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.00032 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000137 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 3.91e-11 |\n", + "| loss_kl | 8.34e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.0112 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.87e-05 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 2.52e-10 |\n", + "| loss_kl | 2.09e-07 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.000405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000295 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.34e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.05e-10 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 6.96e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000103 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.23e-10 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00222 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000182 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00494 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000168 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.4e-10 |\n", + "| loss_kl | 1.37e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | 0.000563 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00039 |\n", + "| loss_pol_entpen | -0.507 |\n", + "| loss_vf_loss | 1.21e-10 |\n", + "| loss_kl | 1.85e-06 |\n", + "| loss_ent | 50.7 |\n", + "| ev_tdlam_before | -0.00337 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.74e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | 1.43e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000294 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000151 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.15e-10 |\n", + "| loss_kl | 1.01e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00029 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000101 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.05e-11 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000391 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000339 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.87e-10 |\n", + "| loss_kl | 1.31e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.0022 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000125 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.98e-10 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 1.25e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.00022 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.62e-11 |\n", + "| loss_kl | 1.55e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -7.68e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000179 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.49e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000524 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.33e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000393 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.06e-10 |\n", + "| loss_kl | 2.32e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000656 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000311 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.68e-10 |\n", + "| loss_kl | 1.97e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00304 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000302 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.37e-11 |\n", + "| loss_kl | 2.09e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00533 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.25e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.56e-11 |\n", + "| loss_kl | 3.58e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000161 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000106 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.53e-10 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00267 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000111 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.71e-10 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000118 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000306 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.92e+06 |\n", + "| TimeElapsed | 1.02e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.26e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.99e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0027 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000102 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.38e-10 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000129 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000137 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.73e-11 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -6.69e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000201 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.36e-11 |\n", + "| loss_kl | 1.25e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000568 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.18e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.24e-11 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000772 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.45e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 3.28e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000734 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000216 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.05e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000774 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000103 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.05e-11 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000391 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000299 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.37e-11 |\n", + "| loss_kl | 1.43e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000417 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.59e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.69e-11 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000578 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000214 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.21e-11 |\n", + "| loss_kl | 8.34e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00409 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00031 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000171 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.56e-10 |\n", + "| loss_kl | 8.34e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000363 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.51e-11 |\n", + "| loss_kl | 1.73e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0147 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000162 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.1e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000227 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000101 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00324 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000173 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.17e-11 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00242 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000263 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.04e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000318 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.93e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000103 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.19e-10 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -3.46e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000155 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.74e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00979 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -6.2e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.42e-10 |\n", + "| loss_kl | 2.09e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00254 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.39e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.12e-11 |\n", + "| loss_kl | 3.28e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00745 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000215 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000121 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.46e-10 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00776 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.34e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000239 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.05e-10 |\n", + "| loss_kl | 1.55e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0186 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000202 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.01e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000136 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.77e-11 |\n", + "| loss_kl | 8.05e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000223 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.82e-11 |\n", + "| loss_kl | 8.94e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00214 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000113 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.71e-11 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00148 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.03e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.61e-10 |\n", + "| loss_kl | 3.58e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00914 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.88e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.1e-11 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000307 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000157 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -2.34e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.47e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00119 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000101 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.82e-10 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000676 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.39e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.18e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000387 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000313 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.36e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.77e-10 |\n", + "| loss_kl | 4.47e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000234 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000145 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.85e-11 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00435 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000115 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.28e-11 |\n", + "| loss_kl | 5.96e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0356 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.03e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000119 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.64e-11 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000616 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000177 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.27e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000502 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000194 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.23e-11 |\n", + "| loss_kl | 7.75e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000483 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000307 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.94e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.23e-10 |\n", + "| loss_kl | 1.01e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00466 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.91e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.21e-11 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00622 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.34e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.06e-11 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00165 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.84e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.76e-10 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00164 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000127 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.55e-11 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0102 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.18e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.46e-11 |\n", + "| loss_kl | 2.38e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00177 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000316 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000111 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000646 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000309 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000205 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.24e-11 |\n", + "| loss_kl | 6.56e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000309 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.36e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.79e-11 |\n", + "| loss_kl | 5.07e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00675 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000309 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000144 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.89e-11 |\n", + "| loss_kl | 3.58e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000774 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000309 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000173 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.48e-10 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00131 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000309 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.35e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.54e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.0087 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.88e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.02 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000141 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.39e-11 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0074 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000149 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.92e-11 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000784 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000302 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.57e-11 |\n", + "| loss_kl | 1.07e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00122 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000283 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.03e-11 |\n", + "| loss_kl | 1.25e-06 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00577 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000305 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.95e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000182 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.03e-10 |\n", + "| loss_kl | 7.15e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000358 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000122 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.75e-10 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00895 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.49e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.41e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00074 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000138 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.57e-11 |\n", + "| loss_kl | 3.87e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00363 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000123 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.65e-11 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00844 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.82e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.59e-10 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000176 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.74e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.38e-10 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -5.5e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.91e-11 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.0128 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.1e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.17e-11 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000224 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.84e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00208 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.69e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.65e-11 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00427 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000259 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.33e-11 |\n", + "| loss_kl | 5.36e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000886 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000292 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -0.000118 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.92e-11 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00286 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.33e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.6e-11 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 7.24e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -9.9e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.03e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00104 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.37e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.21e-11 |\n", + "| loss_kl | 2.38e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000575 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000133 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.34e-11 |\n", + "| loss_kl | 3.58e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000808 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.04e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.14e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.04e-11 |\n", + "| loss_kl | 4.17e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000677 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000144 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.45e-11 |\n", + "| loss_kl | 4.77e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00193 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.07e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.48e-11 |\n", + "| loss_kl | 1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000858 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.54e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.85e-11 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.0029 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.14e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.15e-11 |\n", + "| loss_kl | -8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00115 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.00011 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.77e-10 |\n", + "| loss_kl | 2.68e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 2.83e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000296 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.36e+03 |\n", + "| TimestepsSoFar | 1.96e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.64e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.18e-11 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00681 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000111 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.04e-11 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000405 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -0.0001 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.63e-11 |\n", + "| loss_kl | 1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00189 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000165 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.81e-11 |\n", + "| loss_kl | 5.07e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00107 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.15e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.6e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00244 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.1e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000156 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.7e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.57e-10 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000954 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000125 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.86e-11 |\n", + "| loss_kl | 1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000929 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -5.68e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.85e-10 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 3.62e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.71e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.72e-11 |\n", + "| loss_kl | 2.09e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00551 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.19e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.42e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00087 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.31e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.52e-11 |\n", + "| loss_kl | 3.28e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00366 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00029 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.13e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.76e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000182 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000287 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.03e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.02e-11 |\n", + "| loss_kl | 2.98e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000144 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000287 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.67e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.17e-10 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000207 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000287 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.58e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.5e-11 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000287 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.12e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.18e-10 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000591 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000287 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.97e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -0.000119 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.21e-11 |\n", + "| loss_kl | 1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00241 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.16e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.03e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00263 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.85e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.11e-10 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000533 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.58e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.13e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00432 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.23e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.44e-10 |\n", + "| loss_kl | -8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00108 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -6.09e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.41e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00975 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00028 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.61e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.41e-11 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00211 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.17e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.59e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00459 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.88e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.36e-10 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -3.58e-07 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.3e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.43e-11 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000688 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -4.2e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.7e-11 |\n", + "| loss_kl | 2.38e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000175 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.54e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.37e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00133 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000274 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.37e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.53e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.28e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00469 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -9.15e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.22e-11 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000883 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.18e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.78e-11 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00194 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.72e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.79e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00182 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.05e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.57e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.43e-11 |\n", + "| loss_kl | 8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00727 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.62e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.81e-11 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00718 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000275 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.37e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.46e-11 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00163 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.81e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.49e-11 |\n", + "| loss_kl | -1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000364 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.95e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.62e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00253 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.81e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.08e-10 |\n", + "| loss_kl | -8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00281 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -2.6e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.6e-11 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00185 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000263 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.98e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.71e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.03e-11 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00291 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.71e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.74e-11 |\n", + "| loss_kl | -8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00085 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.34e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 8.01e-11 |\n", + "| loss_kl | 2.38e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00789 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.5e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.3e-11 |\n", + "| loss_kl | -1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00504 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.59e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.52e-10 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000199 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.7e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.58e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0011 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000261 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -1.25e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.62e-11 |\n", + "| loss_kl | -1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0132 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -4.67e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.41e-11 |\n", + "| loss_kl | 1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00818 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.77e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 3.8e-11 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.53e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.39e-11 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.0145 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.28e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.49e-11 |\n", + "| loss_kl | 1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00111 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -5.39e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 4.76e-11 |\n", + "| loss_kl | -1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.0021 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000258 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.57e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.85e-11 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 4.65e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | 2.05e-08 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.04e-10 |\n", + "| loss_kl | -5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00316 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.45e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.19e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00465 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.71e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.004 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.35e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.66e-11 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00683 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.41e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 6.5e-11 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.000903 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000256 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.38e+03 |\n", + "| TimestepsSoFar | 1.99e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.53e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.3e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 4.94e-05 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.46e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.2e-11 |\n", + "| loss_kl | 2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.00346 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -8.12e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.29e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00154 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -7.46e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.28e-10 |\n", + "| loss_kl | -1.79e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00473 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.31e-05 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.31e-10 |\n", + "| loss_kl | 0 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00278 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.00025 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "------------------------------\n", + "| loss_pol_surr | -5.1e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 5.08e-11 |\n", + "| loss_kl | 1.19e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 9.3e-06 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 1 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.49e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 7.21e-11 |\n", + "| loss_kl | -1.49e-07 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000868 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "-------------------------------\n", + "| loss_pol_surr | -1.57e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 2.48e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000488 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -3.21e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 9.04e-11 |\n", + "| loss_kl | 5.96e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.000919 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -1.98e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.96e-10 |\n", + "| loss_kl | -2.98e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | -0.006 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n", + "-------------------------------\n", + "| loss_pol_surr | -2.9e-06 |\n", + "| loss_pol_entpen | -0.508 |\n", + "| loss_vf_loss | 1.12e-10 |\n", + "| loss_kl | -8.94e-08 |\n", + "| loss_ent | 50.8 |\n", + "| ev_tdlam_before | 0.00103 |\n", + "| EpLenMean | 1.44e+03 |\n", + "| EpRewMean | 0.000252 |\n", + "| EpThisIter | 0 |\n", + "| EpisodesSoFar | 1.39e+03 |\n", + "| TimestepsSoFar | 2e+06 |\n", + "| TimeElapsed | 1.06e+04 |\n", + "-------------------------------\n" ] } ], @@ -1010,21 +57825,21 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 15, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:06.821845Z", - "start_time": "2017-07-23T18:11:06.804030+08:00" + "end_time": "2017-07-23T13:16:32.472414Z", + "start_time": "2017-07-23T21:16:32.446719+08:00" } }, "outputs": [ { "data": { "text/plain": [ - "([], [])" + "([1440], [-0.00040950590394714262])" ] }, - "execution_count": 20, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -1035,11 +57850,11 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 16, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:39.509712Z", - "start_time": "2017-07-23T18:11:39.492070+08:00" + "end_time": "2017-07-23T13:16:32.504604Z", + "start_time": "2017-07-23T21:16:32.474787+08:00" } }, "outputs": [], @@ -1063,11 +57878,11 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 17, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:40.496974Z", - "start_time": "2017-07-23T18:11:40.338213+08:00" + "end_time": "2017-07-23T13:16:32.735152Z", + "start_time": "2017-07-23T21:16:32.507531+08:00" } }, "outputs": [], @@ -1089,11 +57904,11 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 18, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:41.789382Z", - "start_time": "2017-07-23T18:11:41.769164+08:00" + "end_time": "2017-07-23T13:16:32.762154Z", + "start_time": "2017-07-23T21:16:32.736927+08:00" }, "collapsed": true }, @@ -1114,11 +57929,11 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 19, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:42.186269Z", - "start_time": "2017-07-23T18:11:42.169431+08:00" + "end_time": "2017-07-23T13:16:32.794613Z", + "start_time": "2017-07-23T21:16:32.765489+08:00" }, "collapsed": true }, @@ -1129,11 +57944,11 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 20, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:46.509356Z", - "start_time": "2017-07-23T18:11:46.481675+08:00" + "end_time": "2017-07-23T13:16:32.825131Z", + "start_time": "2017-07-23T21:16:32.796295+08:00" }, "collapsed": true }, @@ -1146,11 +57961,11 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 25, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:47.531819Z", - "start_time": "2017-07-23T18:11:47.449602+08:00" + "end_time": "2017-07-23T23:11:21.111411Z", + "start_time": "2017-07-24T07:11:21.027828+08:00" } }, "outputs": [ @@ -1160,7 +57975,7 @@ "7613" ] }, - "execution_count": 26, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -1182,11 +57997,11 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 26, "metadata": { "ExecuteTime": { - "end_time": "2017-07-23T10:11:53.770343Z", - "start_time": "2017-07-23T18:11:53.753539+08:00" + "end_time": "2017-07-23T23:11:21.265014Z", + "start_time": "2017-07-24T07:11:21.246915+08:00" } }, "outputs": [], @@ -1203,10 +58018,11 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 27, "metadata": { "ExecuteTime": { - "start_time": "2017-07-23T10:11:54.679Z" + "end_time": "2017-07-23T23:12:01.515980Z", + "start_time": "2017-07-24T07:11:21.424480+08:00" } }, "outputs": [], @@ -1220,18 +58036,51 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 29, "metadata": { "ExecuteTime": { - "start_time": "2017-07-23T10:11:59.800Z" + "end_time": "2017-07-24T00:06:22.397473Z", + "start_time": "2017-07-24T08:06:21.620356+08:00" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "APV (Accumulated portfolio value): \t 7.255540\n", + "SR (Sharpe ratio): \t 0.158198\n", + "MDD (max drawdown): \t-39.092100%\n", + "MDR (mean_market_return): \t 27.985419\n", + "\n" + ] + }, + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd4AAAFhCAYAAADeAstjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "df = pd.DataFrame(env_test.infos)\n", "df.index=df['index']\n", "\n", - "s=sharpe(df.rate_of_return+1)\n", + "s=sharpe(df.rate_of_return)\n", "mdd=MDD(df.rate_of_return+1)\n", "mean_market_return=df.mean_market_returns.cumprod().iloc[-1]\n", "print('APV (Accumulated portfolio value): \\t{: 2.6f}'.format(df.portfolio_value.iloc[-1]))\n", @@ -1246,6 +58095,15 @@ "plt.legend()" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, { "cell_type": "code", "execution_count": null, diff --git a/keras-ddpg.ipynb b/keras-ddpg.ipynb index e494bdd..49674c0 100644 --- a/keras-ddpg.ipynb +++ b/keras-ddpg.ipynb @@ -5,8 +5,8 @@ "execution_count": 1, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:31.840071Z", - "start_time": "2017-07-22T06:44:29.318392+08:00" + "end_time": "2017-07-23T06:09:38.432291Z", + "start_time": "2017-07-23T14:09:37.784671+08:00" } }, "outputs": [ @@ -50,8 +50,8 @@ "execution_count": 2, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:50.345515Z", - "start_time": "2017-07-22T06:44:31.841961+08:00" + "end_time": "2017-07-23T06:09:54.958396Z", + "start_time": "2017-07-23T14:09:38.433930+08:00" } }, "outputs": [ @@ -85,8 +85,8 @@ "execution_count": 3, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:50.372998Z", - "start_time": "2017-07-22T06:44:50.347438+08:00" + "end_time": "2017-07-23T06:09:54.990899Z", + "start_time": "2017-07-23T14:09:54.960526+08:00" }, "collapsed": true }, @@ -103,14 +103,26 @@ "execution_count": 4, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:51.235603Z", - "start_time": "2017-07-22T06:44:50.374433+08:00" - }, - "collapsed": true + "end_time": "2017-07-23T06:09:55.020046Z", + "start_time": "2017-07-23T14:09:54.993182+08:00" + } }, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f'" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "window_length = 50" + "window_length = 50\n", + "save_path= 'outputs/agent_portfolio-ddpg-keras/{}_weights.h5f'.format('2017-07-21_')\n", + "save_path" ] }, { @@ -127,8 +139,8 @@ "execution_count": 5, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:51.785866Z", - "start_time": "2017-07-22T06:44:51.237294+08:00" + "end_time": "2017-07-23T06:09:55.050521Z", + "start_time": "2017-07-23T14:09:55.021418+08:00" }, "collapsed": true }, @@ -142,10 +154,9 @@ "execution_count": 6, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:44:53.317597Z", - "start_time": "2017-07-22T06:44:51.787705+08:00" - }, - "collapsed": true + "end_time": "2017-07-23T06:09:55.223396Z", + "start_time": "2017-07-23T14:09:55.052342+08:00" + } }, "outputs": [], "source": [ @@ -190,11 +201,11 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 7, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:48.162286Z", - "start_time": "2017-07-22T06:45:47.642688+08:00" + "end_time": "2017-07-23T06:09:55.628200Z", + "start_time": "2017-07-23T14:09:55.225321+08:00" }, "scrolled": true }, @@ -206,27 +217,27 @@ "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", - "input_2 (InputLayer) (None, 1, 5, 50, 3) 0 \n", + "input_1 (InputLayer) (None, 1, 5, 50, 3) 0 \n", "_________________________________________________________________\n", - "reshape_3 (Reshape) (None, 5, 50, 3) 0 \n", + "reshape_1 (Reshape) (None, 5, 50, 3) 0 \n", "_________________________________________________________________\n", - "conv2d_6 (Conv2D) (None, 5, 48, 2) 20 \n", + "conv2d_1 (Conv2D) (None, 5, 48, 2) 20 \n", "_________________________________________________________________\n", - "batch_normalization_9 (Batch (None, 5, 48, 2) 8 \n", + "batch_normalization_1 (Batch (None, 5, 48, 2) 8 \n", "_________________________________________________________________\n", - "conv2d_7 (Conv2D) (None, 5, 1, 20) 1940 \n", + "conv2d_2 (Conv2D) (None, 5, 1, 20) 1940 \n", "_________________________________________________________________\n", - "batch_normalization_10 (Batc (None, 5, 1, 20) 80 \n", + "batch_normalization_2 (Batch (None, 5, 1, 20) 80 \n", "_________________________________________________________________\n", - "conv2d_8 (Conv2D) (None, 5, 1, 1) 21 \n", + "conv2d_3 (Conv2D) (None, 5, 1, 1) 21 \n", "_________________________________________________________________\n", - "batch_normalization_11 (Batc (None, 5, 1, 1) 4 \n", + "batch_normalization_3 (Batch (None, 5, 1, 1) 4 \n", "_________________________________________________________________\n", - "flatten_3 (Flatten) (None, 5) 0 \n", + "flatten_1 (Flatten) (None, 5) 0 \n", "_________________________________________________________________\n", - "dense_6 (Dense) (None, 6) 36 \n", + "dense_1 (Dense) (None, 6) 36 \n", "_________________________________________________________________\n", - "activation_6 (Activation) (None, 6) 0 \n", + "activation_1 (Activation) (None, 6) 0 \n", "=================================================================\n", "Total params: 2,109\n", "Trainable params: 2,063\n", @@ -238,48 +249,48 @@ "====================================================================================================\n", "observation_input (InputLayer) (None, 1, 5, 50, 3) 0 \n", "____________________________________________________________________________________________________\n", - "reshape_4 (Reshape) (None, 5, 50, 3) 0 observation_input[0][0] \n", + "reshape_2 (Reshape) (None, 5, 50, 3) 0 observation_input[0][0] \n", "____________________________________________________________________________________________________\n", - "conv2d_9 (Conv2D) (None, 5, 48, 2) 20 reshape_4[0][0] \n", + "conv2d_4 (Conv2D) (None, 5, 48, 2) 20 reshape_2[0][0] \n", "____________________________________________________________________________________________________\n", - "batch_normalization_12 (BatchNor (None, 5, 48, 2) 8 conv2d_9[0][0] \n", + "batch_normalization_4 (BatchNorm (None, 5, 48, 2) 8 conv2d_4[0][0] \n", "____________________________________________________________________________________________________\n", - "conv2d_10 (Conv2D) (None, 5, 1, 20) 1940 batch_normalization_12[0][0] \n", + "conv2d_5 (Conv2D) (None, 5, 1, 20) 1940 batch_normalization_4[0][0] \n", "____________________________________________________________________________________________________\n", - "batch_normalization_13 (BatchNor (None, 5, 1, 20) 80 conv2d_10[0][0] \n", + "batch_normalization_5 (BatchNorm (None, 5, 1, 20) 80 conv2d_5[0][0] \n", "____________________________________________________________________________________________________\n", "action_input (InputLayer) (None, 6) 0 \n", "____________________________________________________________________________________________________\n", - "flatten_4 (Flatten) (None, 100) 0 batch_normalization_13[0][0] \n", + "flatten_2 (Flatten) (None, 100) 0 batch_normalization_5[0][0] \n", "____________________________________________________________________________________________________\n", - "concatenate_2 (Concatenate) (None, 106) 0 action_input[0][0] \n", - " flatten_4[0][0] \n", + "concatenate_1 (Concatenate) (None, 106) 0 action_input[0][0] \n", + " flatten_2[0][0] \n", "____________________________________________________________________________________________________\n", - "dense_7 (Dense) (None, 128) 13696 concatenate_2[0][0] \n", + "dense_2 (Dense) (None, 64) 6848 concatenate_1[0][0] \n", "____________________________________________________________________________________________________\n", - "activation_7 (Activation) (None, 128) 0 dense_7[0][0] \n", + "activation_2 (Activation) (None, 64) 0 dense_2[0][0] \n", "____________________________________________________________________________________________________\n", - "batch_normalization_14 (BatchNor (None, 128) 512 activation_7[0][0] \n", + "batch_normalization_6 (BatchNorm (None, 64) 256 activation_2[0][0] \n", "____________________________________________________________________________________________________\n", - "dense_8 (Dense) (None, 64) 8256 batch_normalization_14[0][0] \n", + "dense_3 (Dense) (None, 32) 2080 batch_normalization_6[0][0] \n", "____________________________________________________________________________________________________\n", - "activation_8 (Activation) (None, 64) 0 dense_8[0][0] \n", + "activation_3 (Activation) (None, 32) 0 dense_3[0][0] \n", "____________________________________________________________________________________________________\n", - "batch_normalization_15 (BatchNor (None, 64) 256 activation_8[0][0] \n", + "batch_normalization_7 (BatchNorm (None, 32) 128 activation_3[0][0] \n", "____________________________________________________________________________________________________\n", - "dense_9 (Dense) (None, 32) 2080 batch_normalization_15[0][0] \n", + "dense_4 (Dense) (None, 16) 528 batch_normalization_7[0][0] \n", "____________________________________________________________________________________________________\n", - "activation_9 (Activation) (None, 32) 0 dense_9[0][0] \n", + "activation_4 (Activation) (None, 16) 0 dense_4[0][0] \n", "____________________________________________________________________________________________________\n", - "batch_normalization_16 (BatchNor (None, 32) 128 activation_9[0][0] \n", + "batch_normalization_8 (BatchNorm (None, 16) 64 activation_4[0][0] \n", "____________________________________________________________________________________________________\n", - "dense_10 (Dense) (None, 1) 33 batch_normalization_16[0][0] \n", + "dense_5 (Dense) (None, 1) 17 batch_normalization_8[0][0] \n", "____________________________________________________________________________________________________\n", - "activation_10 (Activation) (None, 1) 0 dense_10[0][0] \n", + "activation_5 (Activation) (None, 1) 0 dense_5[0][0] \n", "====================================================================================================\n", - "Total params: 27,009\n", - "Trainable params: 26,517\n", - "Non-trainable params: 492\n", + "Total params: 11,969\n", + "Trainable params: 11,701\n", + "Non-trainable params: 268\n", "____________________________________________________________________________________________________\n", "None\n" ] @@ -356,10 +367,6 @@ "y = Flatten()(y)\n", "\n", "x = concatenate([action_input, y])\n", - "x = Dense(128)(x)\n", - "x = Activation('relu')(x)\n", - "x = BatchNormalization()(x)\n", - "\n", "x = Dense(64)(x)\n", "x = Activation('relu')(x)\n", "x = BatchNormalization()(x)\n", @@ -368,6 +375,10 @@ "x = Activation('relu')(x)\n", "x = BatchNormalization()(x)\n", "\n", + "x = Dense(16)(x)\n", + "x = Activation('relu')(x)\n", + "x = BatchNormalization()(x)\n", + "\n", "x = Dense(1)(x)\n", "x = Activation('linear')(x)\n", "critic = Model(inputs=[action_input, observation_input], outputs=x)\n", @@ -383,21 +394,147 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 8, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:51.940197Z", - "start_time": "2017-07-22T06:45:49.715257+08:00" + "end_time": "2017-07-23T06:09:55.660715Z", + "start_time": "2017-07-23T14:09:55.630064+08:00" + } + }, + "outputs": [], + "source": [ + "# # prioritised experience memory, lets make the tensorforce one work for keras-rl\n", + "# # https://github.com/matthiasplappert/keras-rl/blob/master/rl/memory.py#L115\n", + "# # https://github.com/reinforceio/tensorforce/blob/master/tensorforce/core/memories/prioritized_replay.py\n", + "# from tensorforce.core.memories import PrioritizedReplay\n", + "# from collections import namedtuple\n", + "# Experience = namedtuple('Experience',\n", + "# 'state0, action, reward, state1, terminal1')\n", + "\n", + "\n", + "# class KRLPrioritizedReplay(PrioritizedReplay):\n", + "# def get_recent_state(self, current_observation):\n", + "# return current_observation\n", + "\n", + "# def sample(self, batch_size, batch_idxs=None):\n", + "# tensorforce_batch = super().get_batch(batch_size)\n", + "# experiences = []\n", + "# # now convert dict(states=states, actions=actions, rewards=rewards, terminals=terminals, internals=internals)\n", + "# # into Experience = namedtuple('Experience', 'state0, action, reward, state1, terminal1')\n", + "# for i in range(len(tensorforce_batch['states'])-1):\n", + "# experiences.append(\n", + "# Experience(\n", + "# state0=tensorforce_batch['states'][i],\n", + "# action=tensorforce_batch['action'][i],\n", + "# reward=tensorforce_batch['reward'][i],\n", + "# state1=tensorforce_batch['states'][i+1],\n", + "# terminal1=tensorforce_batch['terminals'][i+1],\n", + "# ))\n", + "# return experiences\n", + "\n", + "# def append(self, observation, action, reward, terminal, training=True):\n", + "# \"\"\"Backwards: Store most recent experience in memory.\"\"\"\n", + "# actions = dict([(name, action[i]) for i, name in enumerate(self.action_spec.keys())])\n", + "# states = dict([(name, state[i]) for i, name in enumerate(self.state_spec.keys())])\n", + "# return super().add_observation(\n", + "# state=states,\n", + "# action=actions,\n", + "# reward=reward,\n", + "# terminal=terminal,\n", + "# internal=[])\n", + "\n", + "# @property\n", + "# def nb_entries(self):\n", + "# return len(self.observations)\n", + "\n", + "# def get_config(self):\n", + "# config = {\n", + "# 'window_length': self.window_length,\n", + "# 'ignore_episode_boundaries': self.ignore_episode_boundaries,\n", + "# 'limit': self.limit\n", + "# }\n", + "# return config\n", + " \n", + " \n", + "# # test\n", + "# from tensorforce.config import Configuration\n", + "# # Configuration.from_json\n", + "# states={\n", + "# 'state':dict(shape=tuple(env.observation_space.shape), type='float'),\n", + "# }\n", + "# actions={'action' + str(n): dict(continuous=True) for n in range(env.action_space.shape[0])}\n", + "# config = Configuration(\n", + "# states=states,\n", + "# actions=actions,\n", + "# )\n", + "\n", + "# from rl.memory import SequentialMemory\n", + "# memory0 = SequentialMemory(limit=10000, window_length=1)\n", + "# memory1 = KRLPrioritizedReplay(\n", + "# capacity=10000,\n", + "# states_config=config.states,\n", + "# actions_config=config.actions,\n", + "# prioritization_weight=1.0\n", + "# )\n", + "\n", + "\n", + "# observation = np.zeros(states['state']['shape'])\n", + "# action = [0.5 for i in actions]\n", + "# reward=0.5\n", + "# terminal=False\n", + "\n", + "# for _ in range(10):\n", + "# memory0.append(observation, action, reward, terminal, training=True)\n", + "# state0 = memory0.get_recent_state(observation)\n", + "# sample0 = memory0.sample(1)\n", + "\n", + "\n", + "# for _ in range(10):\n", + "# memory1.append(observation, action, reward, terminal, training=True)\n", + "# state1 = memory1.get_recent_state(observation)\n", + "# sample1 = memory1.sample(1)\n", + "\n", + "# assert sample0==sample1\n", + "\n", + "\n", + "# TODO make batch return state1 https://github.com/matthiasplappert/keras-rl/blob/master/rl/memory.py#L153" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": true + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-23T06:09:57.619763Z", + "start_time": "2017-07-23T14:09:55.662424+08:00" } }, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 15, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -411,10 +548,10 @@ "# We configure and compile our agent.\n", "\n", "# We are providing the last 50 steps so we don't need memory, use window_lenght=1 as placeholder\n", - "memory = SequentialMemory(limit=1000, window_length=1)\n", + "memory = SequentialMemory(limit=100000, window_length=1)\n", "\n", "random_process = OrnsteinUhlenbeckProcess(\n", - " size=nb_actions, theta=.15, mu=0., sigma=.3)\n", + " size=nb_actions, theta=.15, mu=0., sigma=.1)\n", "\n", "agent = DDPGAgent(\n", " nb_actions=nb_actions,\n", @@ -424,16 +561,30 @@ " random_process=random_process,\n", " memory=memory,\n", " batch_size=50,\n", - " nb_steps_warmup_critic=30,\n", - " nb_steps_warmup_actor=30, \n", + " nb_steps_warmup_critic=150,\n", + " nb_steps_warmup_actor=150, \n", " gamma=.00, # discounted factor of zero as per paper\n", " target_model_update=1e-3\n", ")\n", "\n", - "agent.compile(Adam(lr=3e-5), metrics=['mse'])\n", + "# agent.compile(Adam(lr=3e-5), metrics=['mse'])\n", + "# agent.compile(Adam(lr=1e-3), metrics=['mse'])\n", + "agent.compile(Adam(lr=.001, clipnorm=1.), metrics=['mae'])\n", "agent" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-23T06:06:00.585378Z", + "start_time": "2017-07-23T14:06:00.562162+08:00" + } + }, + "outputs": [], + "source": [] + }, { "cell_type": "markdown", "metadata": {}, @@ -443,11 +594,11 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 10, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:51.967418Z", - "start_time": "2017-07-22T06:45:51.941864+08:00" + "end_time": "2017-07-23T06:09:57.647349Z", + "start_time": "2017-07-23T14:09:57.621300+08:00" }, "collapsed": true }, @@ -458,11 +609,11 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 11, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:52.907859Z", - "start_time": "2017-07-22T06:45:52.866949+08:00" + "end_time": "2017-07-23T06:09:57.675197Z", + "start_time": "2017-07-23T14:09:57.649151+08:00" }, "collapsed": true }, @@ -483,11 +634,11 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 12, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:53.125434Z", - "start_time": "2017-07-22T06:45:53.090579+08:00" + "end_time": "2017-07-23T06:09:57.719372Z", + "start_time": "2017-07-23T14:09:57.676651+08:00" }, "collapsed": true }, @@ -532,28 +683,28 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 13, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:45:53.880121Z", - "start_time": "2017-07-22T06:45:53.858142+08:00" + "end_time": "2017-07-23T06:09:57.743581Z", + "start_time": "2017-07-23T14:09:57.720934+08:00" }, "collapsed": true }, "outputs": [], "source": [ - "from rl.callbacks import ModelIntervalCheckpoint\n", - "save_path= 'outputs/agent_portfolio-ddpg-keras/agent_{}_weights.h5f'.format('portfolio-ddpg-keras-rl')" + "from rl.callbacks import ModelIntervalCheckpoint\n" ] }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 14, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T22:46:06.253031Z", - "start_time": "2017-07-22T06:46:06.202048+08:00" - } + "end_time": "2017-07-23T06:09:58.248540Z", + "start_time": "2017-07-23T14:09:57.745131+08:00" + }, + "collapsed": true }, "outputs": [], "source": [ @@ -562,11 +713,11 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 15, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T03:53:15.782271Z", - "start_time": "2017-07-22T07:01:45.394772+08:00" + "end_time": "2017-07-23T06:52:21.893146Z", + "start_time": "2017-07-23T14:09:58.251708+08:00" }, "scrolled": true }, @@ -574,7 +725,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "0344e493c55244b6b076571c2168917f" + "model_id": "70a9dbd48c4344c7a56fec77e30f23b8" } }, "metadata": {}, @@ -587,473 +738,76 @@ "Training for 2000000.0 steps ...\n", "Training for 2000000.0 steps ...\n", "Interval 1 (0 steps performed)\n", + " 1440/2000000.0: episode: 1, duration: 39.401s, episode steps: 1440, steps per second: 37, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.079 [-0.449, 0.807], mean observation: 1.006 [0.716, 1.260], loss: 0.000000, mean_absolute_error: 0.000026, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.213516 [ 1.213516, 1.213516]\n", + "cash_bias : 0.317508 [ 0.317508, 0.317508]\n", + "max_drawdown : -0.112905 [ -0.112905, -0.112905]\n", + "mean_market_return : 1.203628 [ 1.203628, 1.203628]\n", + "sharpe : 0.158765 [ 0.158765, 0.158765]\n", "\n", - " 1440/2000000.0: episode: 1, duration: 44.183s, episode steps: 1440, steps per second: 33, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.181 [-1.304, 1.332], mean observation: 1.003 [0.691, 2.192], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.594360 [ 1.594360, 1.594360]\n", - "cash_bias : 0.290511 [ 0.290511, 0.290511]\n", - "max_drawdown : -0.017700 [ -0.017700, -0.017700]\n", - "mean_market_return : 1.503227 [ 1.503227, 1.503227]\n", - "sharpe : 0.279051 [ 0.279051, 0.279051]\n", - "\n", - "6 episodes - episode_reward: 0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.085 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.060 - cash_bias: 0.207 - mean_market_returns: 1.000\n", + "6 episodes - episode_reward: 0.000 [0.000, 0.000] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.262 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.060 - cash_bias: 0.193 - mean_market_returns: 1.000\n", "\n", "Interval 2 (10000 steps performed)\n", - "Step 14400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 15840/2000000.0: episode: 11, duration: 80.006s, episode steps: 1440, steps per second: 18, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: -0.118 [-1.671, 1.564], mean observation: 1.005 [0.574, 1.602], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.473923 [ 0.407480, 3.806590]\n", - "cash_bias : 0.180586 [ 0.013128, 0.365315]\n", - "max_drawdown : -0.458343 [ -1.612398, -0.025062]\n", - "mean_market_return : 1.479344 [ 0.637105, 2.680602]\n", - "sharpe : 0.139583 [ -0.739532, 0.851367]\n", + "Step 14400: saving model to outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f\n", + " 15840/2000000.0: episode: 11, duration: 48.403s, episode steps: 1440, steps per second: 30, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.108 [-0.437, 0.892], mean observation: 1.000 [0.806, 1.179], loss: 0.000000, mean_absolute_error: 0.000058, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.577905 [ 0.932739, 2.036671]\n", + "cash_bias : 0.185535 [ 0.088615, 0.316687]\n", + "max_drawdown : -0.112632 [ -0.265706, 0.000000]\n", + "mean_market_return : 1.660421 [ 0.988435, 2.715450]\n", + "sharpe : 0.323919 [ -0.049854, 0.611510]\n", "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.227 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.700 - cash_bias: 0.178 - mean_market_returns: 1.000\n", + "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.122 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.700 - cash_bias: 0.212 - mean_market_returns: 1.000\n", "\n", "Interval 3 (20000 steps performed)\n", - "Step 28800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.229 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.340 - cash_bias: 0.159 - mean_market_returns: 1.000\n", + "Step 28800: saving model to outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f\n", + "7 episodes - episode_reward: 0.000 [-0.001, 0.000] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.238 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.340 - cash_bias: 0.127 - mean_market_returns: 1.000\n", "\n", "Interval 4 (30000 steps performed)\n", - " 30240/2000000.0: episode: 21, duration: 62.486s, episode steps: 1440, steps per second: 23, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: -0.029 [-1.237, 1.200], mean observation: 1.006 [0.768, 1.602], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.511885 [ 0.818089, 3.297632]\n", - "cash_bias : 0.170617 [ 0.030225, 0.310242]\n", - "max_drawdown : -0.105082 [ -0.370219, -0.000250]\n", - "mean_market_return : 1.408426 [ 0.769638, 2.520138]\n", - "sharpe : 0.246085 [ -0.120012, 0.731422]\n", + " 30240/2000000.0: episode: 21, duration: 44.595s, episode steps: 1440, steps per second: 32, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.218 [-0.413, 1.028], mean observation: 0.999 [0.793, 1.219], loss: 0.000000, mean_absolute_error: 0.000056, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.248745 [ 0.407212, 1.904446]\n", + "cash_bias : 0.156590 [ 0.082655, 0.287145]\n", + "max_drawdown : -0.378910 [ -2.285048, 0.000000]\n", + "mean_market_return : 1.447858 [ 0.958901, 2.005738]\n", + "sharpe : 0.104191 [ -0.685377, 0.620068]\n", "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.352 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.980 - cash_bias: 0.137 - mean_market_returns: 1.000\n", + "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.146 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.980 - cash_bias: 0.200 - mean_market_returns: 1.000\n", "\n", "Interval 5 (40000 steps performed)\n", - "Step 43200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 44640/2000000.0: episode: 31, duration: 60.532s, episode steps: 1440, steps per second: 24, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.432 [-0.730, 1.601], mean observation: 1.003 [0.859, 1.200], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.654337 [ 0.734315, 2.529743]\n", - "cash_bias : 0.149719 [ 0.028282, 0.386525]\n", - "max_drawdown : -0.216970 [ -0.663005, -0.021538]\n", - "mean_market_return : 1.519005 [ 0.442962, 2.432682]\n", - "sharpe : 0.240032 [ -0.089893, 0.532936]\n", + "Step 43200: saving model to outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f\n", + " 44640/2000000.0: episode: 31, duration: 45.267s, episode steps: 1440, steps per second: 32, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.162 [-0.382, 1.237], mean observation: 1.002 [0.714, 1.329], loss: 0.000000, mean_absolute_error: 0.000056, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.219054 [ 0.498454, 2.219928]\n", + "cash_bias : 0.167086 [ 0.022215, 0.295571]\n", + "max_drawdown : -0.422660 [ -2.040575, -0.001453]\n", + "mean_market_return : 1.390501 [ 0.456720, 2.253033]\n", + "sharpe : 0.087768 [ -0.382995, 0.536017]\n", "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.219 - rate_of_return: 0.000 - cost: 0.000 - steps: 718.620 - cash_bias: 0.194 - mean_market_returns: 1.000\n", + "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.175 - rate_of_return: 0.000 - cost: 0.000 - steps: 718.620 - cash_bias: 0.126 - mean_market_returns: 1.000\n", "\n", "Interval 6 (50000 steps performed)\n", - "Step 57600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 59040/2000000.0: episode: 41, duration: 58.156s, episode steps: 1440, steps per second: 25, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.021 [-0.927, 1.287], mean observation: 0.995 [0.488, 1.464], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.466347 [ 1.026329, 1.903196]\n", - "cash_bias : 0.208635 [ 0.016432, 0.491537]\n", - "max_drawdown : -0.069684 [ -0.212431, 0.000000]\n", - "mean_market_return : 1.624505 [ 1.028553, 2.206736]\n", - "sharpe : 0.213490 [ 0.035250, 0.320303]\n", + "Step 57600: saving model to outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f\n", + " 59040/2000000.0: episode: 41, duration: 47.461s, episode steps: 1440, steps per second: 30, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.231 [-0.299, 1.025], mean observation: 1.003 [0.814, 1.204], loss: 0.000000, mean_absolute_error: 0.000052, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.463877 [ 0.626685, 3.190795]\n", + "cash_bias : 0.157259 [ 0.046178, 0.282287]\n", + "max_drawdown : -0.227408 [ -0.987281, 0.000000]\n", + "mean_market_return : 1.546166 [ 0.694661, 2.609289]\n", + "sharpe : 0.260935 [ -0.149933, 1.046400]\n", "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.244 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.260 - cash_bias: 0.188 - mean_market_returns: 1.000\n", + "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.201 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.260 - cash_bias: 0.151 - mean_market_returns: 1.000\n", "\n", "Interval 7 (60000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.159 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.900 - cash_bias: 0.154 - mean_market_returns: 1.000\n", + "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_absolute_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.060 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.900 - cash_bias: 0.158 - mean_market_returns: 1.000\n", "\n", "Interval 8 (70000 steps performed)\n", - "Step 72000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 73440/2000000.0: episode: 51, duration: 60.020s, episode steps: 1440, steps per second: 24, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.207 [-1.130, 1.337], mean observation: 0.999 [0.793, 1.189], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.350455 [ 0.860484, 1.950396]\n", - "cash_bias : 0.149423 [ 0.007750, 0.339040]\n", - "max_drawdown : -0.242860 [ -0.788709, -0.007982]\n", - "mean_market_return : 1.543903 [ 1.088251, 1.978090]\n", - "sharpe : 0.223853 [ -0.045842, 0.701498]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.360 - rate_of_return: 0.000 - cost: 0.000 - steps: 720.540 - cash_bias: 0.153 - mean_market_returns: 1.000\n", - "\n", - "Interval 9 (80000 steps performed)\n", - "Step 86400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 87840/2000000.0: episode: 61, duration: 60.764s, episode steps: 1440, steps per second: 24, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.311 [-1.169, 1.319], mean observation: 1.002 [0.859, 1.200], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.516538 [ 0.617458, 2.975510]\n", - "cash_bias : 0.157411 [ 0.048918, 0.337389]\n", - "max_drawdown : -0.242529 [ -0.764312, -0.013177]\n", - "mean_market_return : 1.384925 [ 0.748278, 1.983123]\n", - "sharpe : 0.190810 [ -0.190192, 0.551999]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.281 - rate_of_return: 0.000 - cost: 0.000 - steps: 721.180 - cash_bias: 0.142 - mean_market_returns: 1.000\n", - "\n", - "Interval 10 (90000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.463 - rate_of_return: 0.000 - cost: 0.000 - steps: 721.820 - cash_bias: 0.196 - mean_market_returns: 1.000\n", - "\n", - "Interval 11 (100000 steps performed)\n", - "Step 100800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - " 102240/2000000.0: episode: 71, duration: 60.173s, episode steps: 1440, steps per second: 24, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.338 [-0.593, 2.013], mean observation: 1.006 [0.768, 1.602], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.712620 [ 0.586262, 3.524364]\n", - "cash_bias : 0.177027 [ 0.013535, 0.400723]\n", - "max_drawdown : -0.201248 [ -0.793034, -0.007775]\n", - "mean_market_return : 1.449890 [ 0.535093, 2.789479]\n", - "sharpe : 0.206406 [ -0.347600, 0.618238]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.554 - rate_of_return: 0.000 - cost: 0.000 - steps: 722.460 - cash_bias: 0.164 - mean_market_returns: 1.000\n", - "\n", - "Interval 12 (110000 steps performed)\n", - "Step 115200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 116640/2000000.0: episode: 81, duration: 59.677s, episode steps: 1440, steps per second: 24, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.112 [-1.194, 1.259], mean observation: 1.002 [0.714, 1.329], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.944039 [ 0.155057, 4.785229]\n", - "cash_bias : 0.183107 [ 0.017985, 0.389856]\n", - "max_drawdown : -0.732234 [ -6.409485, 0.000000]\n", - "mean_market_return : 1.484428 [ 0.836086, 2.307973]\n", - "sharpe : 0.174402 [ -0.801079, 0.776428]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.161 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.100 - cash_bias: 0.171 - mean_market_returns: 1.000\n", - "\n", - "Interval 13 (120000 steps performed)\n", - "Step 129600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.254 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.740 - cash_bias: 0.236 - mean_market_returns: 1.000\n", - "\n", - "Interval 14 (130000 steps performed)\n", - " 131040/2000000.0: episode: 91, duration: 60.622s, episode steps: 1440, steps per second: 24, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.456 [-0.691, 1.501], mean observation: 1.000 [0.456, 2.151], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.705976 [ 1.037533, 3.111603]\n", - "cash_bias : 0.202714 [ 0.003384, 0.404770]\n", - "max_drawdown : -0.105421 [ -0.375535, -0.011562]\n", - "mean_market_return : 1.548067 [ 1.024713, 2.073652]\n", - "sharpe : 0.310354 [ 0.040457, 0.572844]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.374 - rate_of_return: 0.000 - cost: 0.000 - steps: 724.380 - cash_bias: 0.154 - mean_market_returns: 1.000\n", - "\n", - "Interval 15 (140000 steps performed)\n", - "Step 144000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 145440/2000000.0: episode: 101, duration: 59.694s, episode steps: 1440, steps per second: 24, episode reward: -0.001, mean reward: -0.000 [-0.000, 0.000], mean action: -0.091 [-1.061, 0.905], mean observation: 1.002 [0.772, 1.398], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.726148 [ 0.202543, 6.728255]\n", - "cash_bias : 0.153086 [ 0.036917, 0.466260]\n", - "max_drawdown : -0.983703 [ -4.524803, -0.033152]\n", - "mean_market_return : 1.415627 [ 0.457147, 1.906132]\n", - "sharpe : 0.058999 [ -0.898475, 0.699889]\n", - "\n", - "7 episodes - episode_reward: -0.000 [-0.001, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: -0.000 - reward: -0.000 - log_return: -0.000 - portfolio_value: 1.027 - rate_of_return: 0.000 - cost: 0.000 - steps: 725.020 - cash_bias: 0.148 - mean_market_returns: 1.000\n", - "\n", - "Interval 16 (150000 steps performed)\n", - "Step 158400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 159840/2000000.0: episode: 111, duration: 59.441s, episode steps: 1440, steps per second: 24, episode reward: 0.001, mean reward: 0.000 [-0.000, 0.000], mean action: 0.290 [-1.227, 2.213], mean observation: 0.999 [0.668, 1.411], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.341393 [ 0.179996, 2.772761]\n", - "cash_bias : 0.160683 [ 0.044232, 0.321196]\n", - "max_drawdown : -0.966955 [ -6.810792, 0.000000]\n", - "mean_market_return : 1.421045 [ 0.437170, 2.379175]\n", - "sharpe : 0.160655 [ -0.872273, 0.988650]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.200 - rate_of_return: 0.000 - cost: 0.000 - steps: 725.660 - cash_bias: 0.177 - mean_market_returns: 1.000\n", - "\n", - "Interval 17 (160000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.357 - rate_of_return: 0.000 - cost: 0.000 - steps: 726.300 - cash_bias: 0.129 - mean_market_returns: 1.000\n", - "\n", - "Interval 18 (170000 steps performed)\n", - "Step 172800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 174240/2000000.0: episode: 121, duration: 59.761s, episode steps: 1440, steps per second: 24, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.074 [-0.954, 1.756], mean observation: 1.000 [0.671, 1.591], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.886839 [ 1.234943, 3.395351]\n", - "cash_bias : 0.117782 [ 0.013228, 0.212199]\n", - "max_drawdown : -0.158390 [ -0.784111, -0.003584]\n", - "mean_market_return : 1.507486 [ 0.912888, 2.115239]\n", - "sharpe : 0.354955 [ 0.097402, 0.523312]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.493 - rate_of_return: 0.000 - cost: 0.000 - steps: 726.940 - cash_bias: 0.144 - mean_market_returns: 1.000\n", - "\n", - "Interval 19 (180000 steps performed)\n", - "Step 187200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 188640/2000000.0: episode: 131, duration: 42.758s, episode steps: 1440, steps per second: 34, episode reward: -0.001, mean reward: -0.000 [-0.000, 0.000], mean action: 0.389 [-0.615, 1.244], mean observation: 1.002 [0.802, 1.398], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.668626 [ 0.125406, 3.654824]\n", - "cash_bias : 0.138927 [ 0.021738, 0.465522]\n", - "max_drawdown : -0.793350 [ -7.263991, 0.000000]\n", - "mean_market_return : 1.500480 [ 0.475625, 2.307281]\n", - "sharpe : 0.090682 [ -1.260924, 0.513489]\n", - "\n", - "6 episodes - episode_reward: -0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: -0.000 - log_return: -0.000 - portfolio_value: 1.103 - rate_of_return: -0.000 - cost: 0.000 - steps: 716.060 - cash_bias: 0.150 - mean_market_returns: 1.000\n", - "\n", - "Interval 20 (190000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.244 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.700 - cash_bias: 0.124 - mean_market_returns: 1.000\n", - "\n", - "Interval 21 (200000 steps performed)\n", - "Step 201600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 203040/2000000.0: episode: 141, duration: 42.946s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: -0.323 [-1.935, 0.664], mean observation: 0.995 [0.411, 1.859], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.521499 [ 0.617075, 3.622397]\n", - "cash_bias : 0.178781 [ 0.022048, 0.386592]\n", - "max_drawdown : -0.312852 [ -1.840343, 0.000000]\n", - "mean_market_return : 1.389151 [ 0.705657, 1.988626]\n", - "sharpe : 0.152642 [ -0.317682, 0.501527]\n", - "\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.510 - rate_of_return: 0.001 - cost: 0.000 - steps: 717.340 - cash_bias: 0.167 - mean_market_returns: 1.000\n", - "\n", - "Interval 22 (210000 steps performed)\n", - "Step 216000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 217440/2000000.0: episode: 151, duration: 42.111s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.130 [-1.287, 1.493], mean observation: 1.001 [0.614, 1.391], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 2.085229 [ 0.592355, 4.187601]\n", - "cash_bias : 0.144383 [ 0.023876, 0.300895]\n", - "max_drawdown : -0.312512 [ -1.341535, 0.000000]\n", - "mean_market_return : 1.682785 [ 0.800379, 2.945651]\n", - "sharpe : 0.328789 [ -0.171059, 1.072071]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.143 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.980 - cash_bias: 0.202 - mean_market_returns: 1.000\n", - "\n", - "Interval 23 (220000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.188 - rate_of_return: 0.000 - cost: 0.000 - steps: 718.620 - cash_bias: 0.140 - mean_market_returns: 1.000\n", - "\n", - "Interval 24 (230000 steps performed)\n", - "Step 230400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 231840/2000000.0: episode: 161, duration: 42.223s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.153 [-0.957, 1.603], mean observation: 1.003 [0.859, 1.200], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.353041 [ 0.730177, 2.855037]\n", - "cash_bias : 0.175942 [ 0.054925, 0.333919]\n", - "max_drawdown : -0.302326 [ -1.052090, -0.006299]\n", - "mean_market_return : 1.343597 [ 1.028168, 2.516642]\n", - "sharpe : 0.145916 [ -0.154478, 0.600302]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.406 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.260 - cash_bias: 0.169 - mean_market_returns: 1.000\n", - "\n", - "Interval 25 (240000 steps performed)\n", - "Step 244800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 246240/2000000.0: episode: 171, duration: 42.063s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.180 [-1.193, 1.280], mean observation: 1.002 [0.772, 1.428], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 2.097437 [ 1.024634, 5.160928]\n", - "cash_bias : 0.159316 [ 0.052932, 0.398416]\n", - "max_drawdown : -0.182138 [ -0.626646, -0.010866]\n", - "mean_market_return : 1.438233 [ 0.978891, 2.244525]\n", - "sharpe : 0.295053 [ 0.035800, 0.816552]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.379 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.900 - cash_bias: 0.143 - mean_market_returns: 1.000\n", - "\n", - "Interval 26 (250000 steps performed)\n", - "Step 259200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.323 - rate_of_return: 0.000 - cost: 0.000 - steps: 720.540 - cash_bias: 0.173 - mean_market_returns: 1.000\n", - "\n", - "Interval 27 (260000 steps performed)\n", - " 260640/2000000.0: episode: 181, duration: 42.456s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.239 [-1.008, 1.703], mean observation: 1.001 [0.546, 1.568], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.699592 [ 1.027996, 2.904053]\n", - "cash_bias : 0.164674 [ 0.016774, 0.335168]\n", - "max_drawdown : -0.166984 [ -0.511628, -0.023091]\n", - "mean_market_return : 1.492718 [ 0.973269, 2.229736]\n", - "sharpe : 0.243357 [ 0.034102, 0.536610]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.438 - rate_of_return: 0.000 - cost: 0.000 - steps: 721.180 - cash_bias: 0.160 - mean_market_returns: 1.000\n", - "\n", - "Interval 28 (270000 steps performed)\n", - "Step 273600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 275040/2000000.0: episode: 191, duration: 45.147s, episode steps: 1440, steps per second: 32, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.113 [-1.084, 1.275], mean observation: 1.003 [0.772, 1.428], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.664715 [ 0.456854, 3.918273]\n", - "cash_bias : 0.176635 [ 0.023738, 0.350580]\n", - "max_drawdown : -0.372458 [ -1.261264, -0.002640]\n", - "mean_market_return : 1.352173 [ 0.743006, 2.146232]\n", - "sharpe : 0.148712 [ -0.568148, 0.671670]\n", - "\n", - "7 episodes - episode_reward: -0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: -0.000 - reward: -0.000 - log_return: -0.000 - portfolio_value: 0.941 - rate_of_return: -0.000 - cost: 0.000 - steps: 721.820 - cash_bias: 0.211 - mean_market_returns: 1.000\n", - "\n", - "Interval 29 (280000 steps performed)\n", - "Step 288000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 289440/2000000.0: episode: 201, duration: 42.208s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.078 [-1.482, 1.855], mean observation: 1.001 [0.766, 1.246], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.235595 [ 0.148613, 2.305946]\n", - "cash_bias : 0.211139 [ 0.074015, 0.471638]\n", - "max_drawdown : -2.047347 [ -8.332630, -0.038622]\n", - "mean_market_return : 1.368645 [ 0.442962, 2.289416]\n", - "sharpe : -0.052367 [ -1.056789, 0.495186]\n", - "\n", - "7 episodes - episode_reward: -0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: -0.000 - reward: -0.000 - log_return: -0.000 - portfolio_value: 1.232 - rate_of_return: -0.000 - cost: 0.000 - steps: 722.460 - cash_bias: 0.201 - mean_market_returns: 1.000\n", - "\n", - "Interval 30 (290000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.266 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.100 - cash_bias: 0.161 - mean_market_returns: 1.000\n", - "\n", - "Interval 31 (300000 steps performed)\n", - "Step 302400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 303840/2000000.0: episode: 211, duration: 42.686s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.306 [-0.916, 1.498], mean observation: 1.003 [0.772, 1.428], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.458586 [ 0.699235, 3.038908]\n", - "cash_bias : 0.146996 [ 0.012374, 0.292332]\n", - "max_drawdown : -0.377410 [ -0.972476, -0.007392]\n", - "mean_market_return : 1.412244 [ 0.513334, 2.086550]\n", - "sharpe : 0.191899 [ -0.045680, 0.492600]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.350 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.740 - cash_bias: 0.143 - mean_market_returns: 1.000\n", - "\n", - "Interval 32 (310000 steps performed)\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Step 316800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 318240/2000000.0: episode: 221, duration: 42.251s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.181 [-0.633, 1.385], mean observation: 1.004 [0.763, 1.483], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.481975 [ 1.056092, 2.392722]\n", - "cash_bias : 0.134164 [ 0.011564, 0.241617]\n", - "max_drawdown : -0.186229 [ -0.612553, 0.000000]\n", - "mean_market_return : 1.509745 [ 1.049210, 1.992326]\n", - "sharpe : 0.207329 [ 0.048098, 0.435800]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.076 - rate_of_return: 0.000 - cost: 0.000 - steps: 724.380 - cash_bias: 0.121 - mean_market_returns: 1.000\n", - "\n", - "Interval 33 (320000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.392 - rate_of_return: 0.000 - cost: 0.000 - steps: 725.020 - cash_bias: 0.203 - mean_market_returns: 1.000\n", - "\n", - "Interval 34 (330000 steps performed)\n", - "Step 331200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 332640/2000000.0: episode: 231, duration: 42.619s, episode steps: 1440, steps per second: 34, episode reward: 0.001, mean reward: 0.000 [-0.000, 0.000], mean action: 0.248 [-1.148, 1.632], mean observation: 0.998 [0.712, 1.470], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.760146 [ 0.736961, 3.929010]\n", - "cash_bias : 0.196908 [ 0.042936, 0.454713]\n", - "max_drawdown : -0.182094 [ -0.503999, 0.000000]\n", - "mean_market_return : 1.449485 [ 1.063526, 1.767541]\n", - "sharpe : 0.247821 [ -0.158185, 0.693678]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.156 - rate_of_return: 0.000 - cost: 0.000 - steps: 725.660 - cash_bias: 0.198 - mean_market_returns: 1.000\n", - "\n", - "Interval 35 (340000 steps performed)\n", - "Step 345600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 347040/2000000.0: episode: 241, duration: 42.203s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.186 [-1.318, 1.250], mean observation: 1.000 [0.766, 1.246], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.249129 [ 0.567965, 2.093722]\n", - "cash_bias : 0.189499 [ 0.094086, 0.384870]\n", - "max_drawdown : -0.392140 [ -0.895713, -0.020708]\n", - "mean_market_return : 1.513570 [ 0.788024, 2.092774]\n", - "sharpe : 0.126834 [ -0.280125, 0.422638]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.376 - rate_of_return: 0.000 - cost: 0.000 - steps: 726.300 - cash_bias: 0.160 - mean_market_returns: 1.000\n", - "\n", - "Interval 36 (350000 steps performed)\n", - "Step 360000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.443 - rate_of_return: 0.000 - cost: 0.000 - steps: 726.940 - cash_bias: 0.219 - mean_market_returns: 1.000\n", - "\n", - "Interval 37 (360000 steps performed)\n", - " 361440/2000000.0: episode: 251, duration: 42.375s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.138 [-1.144, 1.560], mean observation: 1.001 [0.671, 1.591], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.886477 [ 1.071135, 3.063326]\n", - "cash_bias : 0.209227 [ 0.014727, 0.504668]\n", - "max_drawdown : -0.159543 [ -0.473520, 0.000000]\n", - "mean_market_return : 1.685075 [ 0.867424, 2.338639]\n", - "sharpe : 0.314631 [ 0.057232, 0.690450]\n", - "\n", - "6 episodes - episode_reward: 0.000 [-0.001, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.147 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.060 - cash_bias: 0.208 - mean_market_returns: 1.000\n", - "\n", - "Interval 38 (370000 steps performed)\n", - "Step 374400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 375840/2000000.0: episode: 261, duration: 42.855s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.203 [-1.165, 1.308], mean observation: 1.002 [0.859, 1.200], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.272924 [ 0.466934, 1.997194]\n", - "cash_bias : 0.178286 [ 0.005000, 0.482554]\n", - "max_drawdown : -0.473871 [ -2.888397, -0.016942]\n", - "mean_market_return : 1.458548 [ 0.723609, 2.365090]\n", - "sharpe : 0.145703 [ -0.106682, 0.495587]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.156 - rate_of_return: 0.000 - cost: 0.000 - steps: 716.700 - cash_bias: 0.147 - mean_market_returns: 1.000\n", - "\n", - "Interval 39 (380000 steps performed)\n", - "Step 388800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.341 - rate_of_return: 0.000 - cost: 0.000 - steps: 717.340 - cash_bias: 0.191 - mean_market_returns: 1.000\n", - "\n", - "Interval 40 (390000 steps performed)\n", - " 390240/2000000.0: episode: 271, duration: 42.399s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.356 [-0.611, 1.708], mean observation: 0.999 [0.689, 1.290], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.604714 [ 0.647251, 4.117594]\n", - "cash_bias : 0.173673 [ 0.054629, 0.359980]\n", - "max_drawdown : -0.225534 [ -1.014057, 0.000000]\n", - "mean_market_return : 1.402600 [ 1.036820, 1.995323]\n", - "sharpe : 0.240530 [ -0.261323, 0.761704]\n", - "\n", - "7 episodes - episode_reward: 0.001 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.001 - portfolio_value: 1.634 - rate_of_return: 0.001 - cost: 0.000 - steps: 717.980 - cash_bias: 0.194 - mean_market_returns: 1.000\n", - "\n", - "Interval 41 (400000 steps performed)\n", - "Step 403200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 404640/2000000.0: episode: 281, duration: 42.360s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.086 [-1.368, 1.515], mean observation: 1.008 [0.772, 1.398], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 2.179579 [ 0.921390, 5.055359]\n", - "cash_bias : 0.209474 [ 0.076302, 0.495757]\n", - "max_drawdown : -0.084817 [ -0.370159, -0.005763]\n", - "mean_market_return : 1.774603 [ 1.074900, 2.547459]\n", - "sharpe : 0.400088 [ -0.028347, 1.070872]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.208 - rate_of_return: 0.000 - cost: 0.000 - steps: 718.620 - cash_bias: 0.201 - mean_market_returns: 1.000\n", - "\n", - "Interval 42 (410000 steps performed)\n", - "Step 417600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - " 419040/2000000.0: episode: 291, duration: 42.139s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.128 [-1.396, 0.936], mean observation: 1.000 [0.766, 1.194], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.558873 [ 0.954473, 2.200340]\n", - "cash_bias : 0.129541 [ 0.018046, 0.312375]\n", - "max_drawdown : -0.109754 [ -0.401263, -0.004708]\n", - "mean_market_return : 1.525105 [ 0.966760, 2.533780]\n", - "sharpe : 0.271823 [ -0.014139, 0.623485]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.205 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.260 - cash_bias: 0.124 - mean_market_returns: 1.000\n", - "\n", - "Interval 43 (420000 steps performed)\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.286 - rate_of_return: 0.000 - cost: 0.000 - steps: 719.900 - cash_bias: 0.112 - mean_market_returns: 1.000\n", - "\n", - "Interval 44 (430000 steps performed)\n", - "Step 432000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 433440/2000000.0: episode: 301, duration: 42.714s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.355 [-0.796, 1.905], mean observation: 0.999 [0.668, 1.411], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.972488 [ 0.871072, 5.175903]\n", - "cash_bias : 0.124588 [ 0.012806, 0.307573]\n", - "max_drawdown : -0.150890 [ -0.449867, 0.000000]\n", - "mean_market_return : 1.707258 [ 1.078934, 2.232539]\n", - "sharpe : 0.270019 [ -0.091228, 0.832003]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.310 - rate_of_return: 0.000 - cost: 0.000 - steps: 720.540 - cash_bias: 0.121 - mean_market_returns: 1.000\n", - "\n", - "Interval 45 (440000 steps performed)\n", - "Step 446400: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 447840/2000000.0: episode: 311, duration: 42.680s, episode steps: 1440, steps per second: 34, episode reward: -0.001, mean reward: -0.000 [-0.000, 0.000], mean action: 0.142 [-0.896, 1.331], mean observation: 1.007 [0.772, 1.398], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.568627 [ 0.353850, 3.015279]\n", - "cash_bias : 0.208563 [ 0.002246, 0.530852]\n", - "max_drawdown : -0.383691 [ -2.063175, 0.000000]\n", - "mean_market_return : 1.573757 [ 0.790430, 2.778477]\n", - "sharpe : 0.218243 [ -0.563946, 0.970981]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.001, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.310 - rate_of_return: 0.000 - cost: 0.000 - steps: 721.180 - cash_bias: 0.246 - mean_market_returns: 1.000\n", - "\n", - "Interval 46 (450000 steps performed)\n", - "7 episodes - episode_reward: -0.000 [-0.003, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: -0.000 - reward: -0.000 - log_return: -0.000 - portfolio_value: 1.140 - rate_of_return: -0.000 - cost: 0.000 - steps: 721.820 - cash_bias: 0.195 - mean_market_returns: 1.000\n", - "\n", - "Interval 47 (460000 steps performed)\n", - "Step 460800: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 462240/2000000.0: episode: 321, duration: 42.485s, episode steps: 1440, steps per second: 34, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.247 [-1.043, 1.280], mean observation: 1.005 [0.772, 1.398], loss: 0.000000, mean_squared_error: 0.000000, mean_q: -0.000000\n", - "accumulated_portfolio_val: 1.176019 [ 0.026074, 2.268019]\n", - "cash_bias : 0.194184 [ 0.032218, 0.372472]\n", - "max_drawdown : -4.835699 [-45.547742, -0.001152]\n", - "mean_market_return : 1.377317 [ 0.449037, 2.246230]\n", - "sharpe : -0.021666 [ -1.512051, 0.411277]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.118 - rate_of_return: 0.000 - cost: 0.000 - steps: 722.460 - cash_bias: 0.204 - mean_market_returns: 1.000\n", - "\n", - "Interval 48 (470000 steps performed)\n", - "Step 475200: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 476640/2000000.0: episode: 331, duration: 42.080s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.189 [-1.061, 1.542], mean observation: 1.001 [0.725, 1.261], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.447233 [ 1.009390, 2.110690]\n", - "cash_bias : 0.167687 [ 0.029594, 0.310451]\n", - "max_drawdown : -0.127205 [ -0.486266, 0.000000]\n", - "mean_market_return : 1.552742 [ 1.068996, 1.916538]\n", - "sharpe : 0.252990 [ 0.022084, 0.482918]\n", - "\n", - "7 episodes - episode_reward: 0.000 [0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.210 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.100 - cash_bias: 0.139 - mean_market_returns: 1.000\n", - "\n", - "Interval 49 (480000 steps performed)\n", - "Step 489600: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.251 - rate_of_return: 0.000 - cost: 0.000 - steps: 723.740 - cash_bias: 0.167 - mean_market_returns: 1.000\n", - "\n", - "Interval 50 (490000 steps performed)\n", - " 491040/2000000.0: episode: 341, duration: 42.530s, episode steps: 1440, steps per second: 34, episode reward: 0.000, mean reward: 0.000 [-0.000, 0.000], mean action: 0.242 [-1.067, 1.733], mean observation: 1.003 [0.708, 1.300], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.490374 [ 0.904625, 2.649029]\n", - "cash_bias : 0.154503 [ 0.033904, 0.402609]\n", - "max_drawdown : -0.179765 [ -0.407778, -0.030432]\n", - "mean_market_return : 1.365217 [ 0.569160, 2.328922]\n", - "sharpe : 0.199229 [ -0.130794, 0.529057]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.000] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.195 - rate_of_return: 0.000 - cost: 0.000 - steps: 724.380 - cash_bias: 0.104 - mean_market_returns: 1.000\n", - "\n", - "Interval 51 (500000 steps performed)\n", - "Step 504000: saving model to outputs/agent_portfolio-ddpg-keras/agent_portfolio-ddpg-keras-rl_weights.h5f\n", - " 505440/2000000.0: episode: 351, duration: 42.255s, episode steps: 1440, steps per second: 34, episode reward: -0.000, mean reward: -0.000 [-0.000, 0.000], mean action: 0.097 [-1.023, 1.095], mean observation: 1.004 [0.755, 1.263], loss: 0.000000, mean_squared_error: 0.000000, mean_q: 0.000000\n", - "accumulated_portfolio_val: 1.305904 [ 0.741632, 1.963140]\n", - "cash_bias : 0.150030 [ 0.005510, 0.275642]\n", - "max_drawdown : -0.165588 [ -0.636185, 0.000000]\n", - "mean_market_return : 1.295655 [ 0.882587, 1.798812]\n", - "sharpe : 0.151015 [ -0.170254, 0.448210]\n", - "\n", - "7 episodes - episode_reward: 0.000 [-0.000, 0.001] - loss: 0.000 - mean_squared_error: 0.000 - mean_q: 0.000 - reward: 0.000 - log_return: 0.000 - portfolio_value: 1.140 - rate_of_return: 0.000 - cost: 0.000 - steps: 725.020 - cash_bias: 0.239 - mean_market_returns: 1.000\n", - "\n", - "Interval 52 (510000 steps performed)\n", - "done, took 17489.548 seconds\n", - "done, took 17489.548 seconds\n" + "Step 72000: saving model to outputs/agent_portfolio-ddpg-keras/2017-07-21__weights.h5f\n", + " 73440/2000000.0: episode: 51, duration: 56.738s, episode steps: 1440, steps per second: 25, episode reward: 0.001, mean reward: 0.000 [-0.000, 0.000], mean action: 0.217 [-0.358, 1.214], mean observation: 1.000 [0.546, 1.568], loss: 0.000000, mean_absolute_error: 0.000051, mean_q: 0.000000\n", + "accumulated_portfolio_val: 1.325440 [ 0.831368, 2.544167]\n", + "cash_bias : 0.153516 [ 0.031240, 0.262192]\n", + "max_drawdown : -0.105198 [ -0.335216, -0.006713]\n", + "mean_market_return : 1.408127 [ 1.013494, 1.890050]\n", + "sharpe : 0.159886 [ -0.188950, 0.521265]\n", + "\n", + "done, took 2543.323 seconds\n", + "done, took 2543.323 seconds\n" ] } ], @@ -1087,12 +841,13 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 16, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T03:53:20.259190Z", - "start_time": "2017-07-22T11:53:19.888141+08:00" - } + "end_time": "2017-07-23T06:52:22.264835Z", + "start_time": "2017-07-23T14:52:21.895982+08:00" + }, + "collapsed": true }, "outputs": [], "source": [ @@ -1111,21 +866,32 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T03:58:21.062800Z", - "start_time": "2017-07-22T11:58:21.017919+08:00" - }, - "collapsed": true + "start_time": "2017-07-23T06:09:37.798Z" + } }, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import tensorforce\n", + "tensorforce" + ] }, { "cell_type": "code", - "execution_count": 45, + "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T03:59:29.899909Z", - "start_time": "2017-07-22T11:58:34.306922+08:00" + "start_time": "2017-07-23T06:09:37.800Z" } }, "outputs": [ @@ -1133,34 +899,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.000, steps: 7613\n", - "APV (Accumulated portfolio value): \t 27.828025\n", - "SR (Sharpe ratio): \t 687.421653\n", - "MDD (max drawdown): \t-17.182768%\n", - "MDR (mean_market_return): \t 2798.541859%\n", - "\n" + "Testing for 1 episodes ...\n" ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 45, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd4AAAFhCAYAAADeAstjAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" } ], "source": [ @@ -1198,87 +938,14 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T04:00:11.951167Z", - "start_time": "2017-07-22T12:00:11.886758+08:00" - } + "start_time": "2017-07-23T06:09:37.802Z" + }, + "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "index\n", - "2017-02-04 08:00:00 [1.0, 0.0, 0.0, 0.0, 0.0, 0.0]\n", - "2017-02-04 08:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 09:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 09:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 10:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 10:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 11:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 11:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 12:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 12:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 13:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 13:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 14:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 14:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 15:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 15:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 16:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 16:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 17:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 17:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 18:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 18:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 19:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 19:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 20:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 20:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 21:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 21:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 22:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-02-04 22:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - " ... \n", - "2017-07-12 08:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 08:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 09:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 09:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 10:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 10:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 11:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 11:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 12:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 12:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 13:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 13:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 14:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 14:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 15:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 15:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 16:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 16:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 17:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 17:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 18:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 18:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 19:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 19:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 20:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 20:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 21:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 21:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 22:00:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "2017-07-12 22:30:00 [0.166613, 0.166793, 0.166595, 0.166476, 0.166...\n", - "Name: weights, Length: 7614, dtype: object" - ] - }, - "execution_count": 47, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# The weights appear to be static, so the model hasn't learnt much :(\n", "df = pd.DataFrame(env_test.infos)\n", @@ -1288,101 +955,13 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2017-07-22T04:00:38.853812Z", - "start_time": "2017-07-22T12:00:35.693506+08:00" + "start_time": "2017-07-23T06:09:37.804Z" } }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.022566\n", - "SR (Sharpe ratio): \t 1338.412318\n", - "MDD (max drawdown): \t-1.431222%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: -0.000, steps: 30\n", - "APV (Accumulated portfolio value): \t 0.998612\n", - "SR (Sharpe ratio): \t 1486.265133\n", - "MDD (max drawdown): \t-0.841634%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.021422\n", - "SR (Sharpe ratio): \t 846.340593\n", - "MDD (max drawdown): \t-2.532473%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.031772\n", - "SR (Sharpe ratio): \t 1346.222680\n", - "MDD (max drawdown): \t-2.232542%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.020095\n", - "SR (Sharpe ratio): \t 1186.772388\n", - "MDD (max drawdown): \t-1.806113%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.000, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.005496\n", - "SR (Sharpe ratio): \t 1799.999325\n", - "MDD (max drawdown): \t-1.132944%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.002, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.064011\n", - "SR (Sharpe ratio): \t 731.235092\n", - "MDD (max drawdown): \t-3.207236%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.026627\n", - "SR (Sharpe ratio): \t 1020.265170\n", - "MDD (max drawdown): \t-1.122229%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: 0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 1.021451\n", - "SR (Sharpe ratio): \t 2545.496061\n", - "MDD (max drawdown): \t-0.860392%\n", - "\n", - "Testing for 1 episodes ...\n", - "Episode 1: reward: -0.001, steps: 30\n", - "APV (Accumulated portfolio value): \t 0.976392\n", - "SR (Sharpe ratio): \t 1089.003243\n", - "MDD (max drawdown): \t-2.371002%\n", - "\n" - ] - }, - { - "data": { - "text/plain": [ - "" - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAewAAAFJCAYAAABZ+x49AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# Lets evaluate a few 30 step intervals\n", "df_test = pd.read_hdf('./data/poloniex_30m.hf',key='test')\n", @@ -1399,9 +978,11 @@ "for i in range(10):\n", " agent.test(env_test, nb_episodes=1, visualize=False)\n", " df = pd.DataFrame(env_test.infos)\n", - " s=sharpe(df.rate_of_return+1)\n", + " s=sharpe(df.rate_of_return)\n", " mdd=MDD(df.rate_of_return+1)\n", + " mean_market_return=df.mean_market_returns.cumprod().iloc[-1]\n", " print('APV (Accumulated portfolio value): \\t{: 2.6f}'.format(df.portfolio_value.iloc[-1]))\n", + " print('MMR (mean_market_return): \\t{: 2.6f}'.format(mean_market_return)) \n", " print('SR (Sharpe ratio): \\t{: 2.6f}'.format( s))\n", " print('MDD (max drawdown): \\t{: 2.6%}'.format( mdd))\n", " print('')\n", @@ -1431,26 +1012,13 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2017-07-21T06:26:38.467490Z", - "start_time": "2017-07-21T14:26:38.428113+08:00" + "start_time": "2017-07-23T06:09:37.807Z" } }, - "outputs": [ - { - "ename": "NameError", - "evalue": "name 'history' is not defined", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;31m# history\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mdf_hist\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mhistory\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhistory\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mdf_hist\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mdf_hist\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'episodes'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf_hist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mNameError\u001b[0m: name 'history' is not defined" - ] - } - ], + "outputs": [], "source": [ "# history\n", "df_hist = pd.DataFrame(history.history)\n", @@ -1463,20 +1031,6 @@ "# g = sns.jointplot(x=\"episodes\", y=\"rewards\", data=history, kind=\"reg\")" ] }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-01T03:02:19.820742Z", - "start_time": "2017-07-01T11:02:19.740692+08:00" - } - }, - "source": [ - "# dummy metrics\n", - "\n", - "TODO" - ] - }, { "cell_type": "code", "execution_count": null, diff --git a/tensorforce-VPG.ipynb b/tensorforce-VPG.ipynb index 4cb877e..d350317 100644 --- a/tensorforce-VPG.ipynb +++ b/tensorforce-VPG.ipynb @@ -19,7 +19,6 @@ "plt.style.use('ggplot')\n", "\n", "# numeric\n", - "import quandl\n", "import numpy as np\n", "from numpy import random\n", "import pandas as pd\n",