wassname/curl
1
0
Fork 0
mirror of https://github.com/wassname/curl.git synced 2026-09-09 11:20:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

logger edit

Browse Source
This commit is contained in:
MishaLaskin
2020-02-08 17:26:22 -08:00
parent 0999558c08
commit ecd207e4ea
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -24,7 +24,7 @@ and go to `localhost:6006` in your browser. If you're running headlessly, try po
The console output is also available in a form:
```
| train | E: 1 | S: 1000 | D: 0.8 s | R: 0.0000 | BR: 0.0000 | ALOSS: 0.0000 | CLOSS: 0.0000 | RLOSS: 0.0000
| train | E: 1 | S: 1000 | D: 0.8 s | R: 0.0000 | BR: 0.0000 | A_LOSS: 0.0000 | CR_LOSS: 0.0000 | CU_LOSS: 0.0000
```
a training entry decodes as:
```
train.py
+2 -2
View File
@@ -106,8 +106,8 @@ def evaluate(env, agent, video, num_episodes, L, step, args):
mean_ep_reward = np.mean(all_ep_rewards)
best_ep_reward = np.max(all_ep_rewards)
L.log('eval/' + prefix + 'mean_episode_reward', mean_ep_reward, step)
L.log('eval/' + prefix + 'best_episode_reward', best_ep_reward, step)
L.log('eval/' + prefix + '_mean_episode_reward', mean_ep_reward, step)
L.log('eval/' + prefix + '_best_episode_reward', best_ep_reward, step)
run_eval_loop(sample_stochastically=True)
run_eval_loop(sample_stochastically=False)