Hugging Face's logo

sdpkjc
/
Humanoid-v4-ppo_fix_continuous_action-seed2

Reinforcement Learning
TensorBoard
cleanrl
Humanoid-v4
deep-reinforcement-learning
custom-implementation
Eval Results
Model card Files Metrics Community
sdpkjc commited on
Commit
cdd3ed8
•
1 Parent(s): 219f2ed

pushing model

Browse files
Files changed (10) hide show
  1. README.md +1 -1
  2. events.out.tfevents.1702950436.4090-171.365895.0 → events.out.tfevents.1704463122.4090-171.155252.0 +1 -1
  3. ppo_fix_continuous_action.py +1 -1
  4. replay.mp4 +0 -0
  5. videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-0.mp4 +0 -0
  6. videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-1.mp4 +0 -0
  7. videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-8.mp4 +0 -0
  8. videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-eval/rl-video-episode-0.mp4 +0 -0
  9. videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-eval/rl-video-episode-1.mp4 +0 -0
  10. videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-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: 640.02 +/- 74.87
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: Humanoid-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 645.97 +/- 116.36
20
  name: mean_reward
21
  verified: false
22
  ---
events.out.tfevents.1702950436.4090-171.365895.0 → events.out.tfevents.1704463122.4090-171.155252.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb2a6ebc1aed47251c585415f54ee0d85cb4e774b2710002c7d0652d7084b963
3
  size 1560407
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dd4d9b3f31216b3fa901d4a9513659519a7eba7b068950871418e85e7d2c05
3
  size 1560407
ppo_fix_continuous_action.py CHANGED
@@ -430,7 +430,7 @@ if __name__ == "__main__":
430
 
431
  # https://github.com/DLR-RM/stable-baselines3/pull/658
432
  for idx, trunc in enumerate(truncations):
433
- if trunc:
434
  real_next_obs = infos["final_observation"][idx]
435
  with torch.no_grad():
436
  terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]
 
430
 
431
  # https://github.com/DLR-RM/stable-baselines3/pull/658
432
  for idx, trunc in enumerate(truncations):
433
+ if trunc and not terminations[idx]:
434
  real_next_obs = infos["final_observation"][idx]
435
  with torch.no_grad():
436
  terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-0.mp4 DELETED
Binary file (190 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-1.mp4 DELETED
Binary file (204 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1702950428-eval/rl-video-episode-8.mp4 DELETED
Binary file (215 kB)
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-eval/rl-video-episode-0.mp4 ADDED
Binary file (267 kB). View file
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-eval/rl-video-episode-1.mp4 ADDED
Binary file (237 kB). View file
 
videos/Humanoid-v4__ppo_fix_continuous_action__2__1704463109-eval/rl-video-episode-8.mp4 ADDED
Binary file (164 kB). View file