Hugging Face's logo

sdpkjc
/
Humanoid-v4-ppo_fix_continuous_action-seed3

Reinforcement Learning
TensorBoard
cleanrl
Humanoid-v4
deep-reinforcement-learning
custom-implementation
Eval Results
Model card Files Metrics Community
sdpkjc commited on
Commit
3ceac33
·
verified ·
1 Parent(s): 3f780c6

pushing model

Browse files
Files changed (11) hide show
  1. README.md +1 -1
  2. events.out.tfevents.1704463191.4090-171.156339.0 → events.out.tfevents.1705702780.3090-172.2624313.0 +2 -2
  3. ppo_fix_continuous_action.cleanrl_model +0 -0
  4. ppo_fix_continuous_action.py +1 -1
  5. replay.mp4 +0 -0
  6. videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-0.mp4 +0 -0
  7. videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-1.mp4 +0 -0
  8. videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-8.mp4 +0 -0
  9. videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-0.mp4 +0 -0
  10. videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-1.mp4 +0 -0
  11. videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-8.mp4 +0 -0
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: Humanoid-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 705.46 +/- 121.82
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: Humanoid-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 814.10 +/- 147.07
20
  name: mean_reward
21
  verified: false
22
  ---
events.out.tfevents.1704463191.4090-171.156339.0 → events.out.tfevents.1705702780.3090-172.2624313.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f31ddf552914720ad52e42b81f1779351e4d1bc2f40ed5a9e1f4562f1e40f041
3
- size 1496689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6a92e1eea6fa143fcd4ac95d9b540fd157e85c5b8e36eeb9a0d71c43965690
3
+ size 1483067
ppo_fix_continuous_action.cleanrl_model CHANGED
Binary files a/ppo_fix_continuous_action.cleanrl_model and b/ppo_fix_continuous_action.cleanrl_model differ
 
ppo_fix_continuous_action.py CHANGED
@@ -198,7 +198,7 @@ class NormalizeReward(gym.core.Wrapper, gym.utils.RecordConstructorArgs):
198
  return obs, rews, terminateds, truncateds, infos
199
 
200
  def reset(self, **kwargs):
201
- self.returns = np.zeros(self.num_envs)
202
  return self.env.reset(**kwargs)
203
 
204
  def normalize(self, rews):
 
198
  return obs, rews, terminateds, truncateds, infos
199
 
200
  def reset(self, **kwargs):
201
+ # self.returns = np.zeros(self.num_envs)
202
  return self.env.reset(**kwargs)
203
 
204
  def normalize(self, rews):
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-0.mp4 DELETED
Binary file (276 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-1.mp4 DELETED
Binary file (244 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1704463180-eval/rl-video-episode-8.mp4 DELETED
Binary file (288 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-0.mp4 ADDED
Binary file (280 kB). View file
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-1.mp4 ADDED
Binary file (212 kB). View file
 
videos/Humanoid-v4__ppo_fix_continuous_action__3__1705702773-eval/rl-video-episode-8.mp4 ADDED
Binary file (260 kB). View file