23 Commits

Author SHA1 Message Date
Ilya Kostrikov baf507f6bf Add pybullet support 2017-10-05 15:57:11 -04:00
Ilya Kostrikov 041e928c05 Merge branch 'master' of github.com:ikostrikov/pytorch-a2c-ppo-acktr 2017-09-27 08:31:22 -04:00
Ilya Kostrikov f4af48b765 Add MuJoCo 2017-09-27 08:29:39 -04:00
Ilya Kostrikov 6e6619c0d7 Add MuJoCo 2017-09-27 08:21:04 -04:00
Ilya Kostrikov 09e75e26ae Add MuJoCo 2017-09-27 08:20:19 -04:00
Ilya Kostrikov 54a0f98180 Recompute old probabilities for PPO, to make continuous actions work with obs filter 2017-09-24 23:00:14 -04:00
Ilya Kostrikov 6ee53d245d Extract repetative code to a function 2017-09-22 21:16:03 -04:00
Ilya Kostrikov f4fc4c6064 Create an act function 2017-09-22 12:29:21 -04:00
Ilya Kostrikov 6c949f291e Store a single log probability of actions 2017-09-21 19:25:16 -04:00
Ilya Kostrikov 475de22519 Create a rollout storage 2017-09-20 19:29:04 -04:00
Ilya Kostrikov ccc261bcb9 Fix a typo 2017-09-19 09:31:49 -04:00
Ilya Kostrikov 9e07584872 Move arguments to a separate file 2017-09-18 23:22:11 -04:00
Ilya Kostrikov ec47ca7ed9 Add KFAC 2017-09-17 23:33:59 -04:00
Ilya Kostrikov 5d29401658 Add PPO 2017-09-17 18:43:45 -04:00
Ilya Kostrikov f09b3a75e4 Add GAE 2017-09-16 20:57:06 -04:00
Ilya Kostrikov eb110220d9 Refactor code to add ppo easier 2017-09-16 17:04:14 -04:00
Ilya Kostrikov 6d17d59f36 Add images 2017-09-14 07:08:50 -04:00
Ilya Kostrikov a4183c5e86 Add visualization 2017-09-13 18:34:13 -04:00
Ilya Kostrikov ae9915a713 Add warning message and more stats 2017-09-09 10:09:03 -04:00
Ilya Kostrikov 9016d17eea Use more meaningful names 2017-09-09 09:48:57 -04:00
Ilya Kostrikov ba37e84b0a Create LICENSE 2017-09-07 20:01:02 -04:00
Ilya Kostrikov 0bca3eb58e Update README.md 2017-09-07 20:00:11 -04:00
Ilya Kostrikov 59890378f4 Initial commit 2017-09-07 19:45:57 -04:00