Hugging Face's logo

sdpkjc
/
HalfCheetah-v4-ppo_fix_continuous_action-seed3

Reinforcement Learning
TensorBoard
cleanrl
HalfCheetah-v4
deep-reinforcement-learning
custom-implementation
Eval Results
Model card Files Metrics Community
sdpkjc commited on
Commit
9432362
•
1 Parent(s): 8cb011d

pushing model

Browse files
Files changed (8) hide show
  1. .gitattributes +3 -0
  2. README.md +1 -1
  3. events.out.tfevents.1702935478.4090-171.243858.0 → events.out.tfevents.1704463466.4090-171.161117.0 +1 -1
  4. ppo_fix_continuous_action.py +1 -1
  5. replay.mp4 +2 -2
  6. videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-0.mp4 +2 -2
  7. videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-1.mp4 +2 -2
  8. videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-8.mp4 +2 -2
.gitattributes CHANGED
@@ -37,3 +37,6 @@ videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval/rl-video-ep
37
  videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
38
  videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
39
  replay.mp4 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
37
  videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
38
  videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
39
  replay.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
41
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
42
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: HalfCheetah-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 1753.29 +/- 28.06
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: HalfCheetah-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 1769.82 +/- 30.38
20
  name: mean_reward
21
  verified: false
22
  ---
events.out.tfevents.1702935478.4090-171.243858.0 → events.out.tfevents.1704463466.4090-171.161117.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f94e3bc5bdfbab799a51c521180cb9f421115ac74bdfe6cd81af8e46766f4d
3
  size 376394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ddb69d746cd2fed1feac1bf153b318c7750707cb5ca1287652cc4be7ade674
3
  size 376394
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
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f437c0185a3adfb17471abc651e09b7e7a7a9d1c84612e58fc1d71f9d24b172d
3
- size 1930476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b82a3826a7af1fd47ec89781850698c523c19f5a665e6be26460727ab9142e3
3
+ size 1887004
videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-0.mp4 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2a38228a11866da74078a19cdfcf438da6799b2a3c17a8452f3f60b1cba915e
3
- size 1873635
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c62b8a9e2721cc1030e3fbd895e51607c27d1ab4f5f283cf76c96f448b5109e
3
+ size 1921617
videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-1.mp4 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f90f6f6b84ef128a062aeede5c98024cda6d86b896352abb4897610db52b6b65
3
- size 1887296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9632d4eb780d14cb62ac3381562fd4fa1aa909a5d6693149647c97aade49cab1
3
+ size 1883127
videos/{HalfCheetah-v4__ppo_fix_continuous_action__3__1702935469-eval → HalfCheetah-v4__ppo_fix_continuous_action__3__1704463457-eval}/rl-video-episode-8.mp4 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f437c0185a3adfb17471abc651e09b7e7a7a9d1c84612e58fc1d71f9d24b172d
3
- size 1930476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b82a3826a7af1fd47ec89781850698c523c19f5a665e6be26460727ab9142e3
3
+ size 1887004