Hugging Face's logo

sdpkjc
/
HalfCheetah-v4-ppo_fix_continuous_action-seed2

Reinforcement Learning
TensorBoard
cleanrl
HalfCheetah-v4
deep-reinforcement-learning
custom-implementation
Eval Results
Model card Files
xet
Metrics Community
sdpkjc commited on
Commit
4ad936a
·
1 Parent(s): aedb585

pushing model

Browse files
Files changed (10) hide show
  1. .gitattributes +4 -0
  2. README.md +4 -4
  3. events.out.tfevents.1700810722.4090-171.1712170.0 → events.out.tfevents.1702935427.4090-171.242716.0 +2 -2
  4. ppo_fix_continuous_action.cleanrl_model +0 -0
  5. ppo_fix_continuous_action.py +1 -1
  6. replay.mp4 +0 -0
  7. videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval/rl-video-episode-1.mp4 +0 -0
  8. videos/{HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval → HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval}/rl-video-episode-0.mp4 +2 -2
  9. videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-1.mp4 +3 -0
  10. videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-8.mp4 +3 -0
.gitattributes CHANGED
@@ -34,3 +34,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
39
+ videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ replay.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: -221.84 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/HalfCheetah-v4-ppo_fix_continuous_action-
46
  curl -OL https://huggingface.co/sdpkjc/HalfCheetah-v4-ppo_fix_continuous_action-seed2/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/sdpkjc/HalfCheetah-v4-ppo_fix_continuous_action-seed2/raw/main/poetry.lock
48
  poetry install --all-extras
49
- python ppo_fix_continuous_action.py --save-model --hf-entity sdpkjc --seed 2 --total-timesteps 2048 --upload-model
50
  ```
51
 
52
  # Hyperparameters
@@ -74,8 +74,8 @@ python ppo_fix_continuous_action.py --save-model --hf-entity sdpkjc --seed 2 --t
74
  'seed': 2,
75
  'target_kl': None,
76
  'torch_deterministic': True,
77
- 'total_timesteps': 2048,
78
- 'track': False,
79
  'update_epochs': 10,
80
  'upload_model': True,
81
  'vf_coef': 0.5,
 
16
  type: HalfCheetah-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 1638.41 +/- 53.59
20
  name: mean_reward
21
  verified: false
22
  ---
 
46
  curl -OL https://huggingface.co/sdpkjc/HalfCheetah-v4-ppo_fix_continuous_action-seed2/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/sdpkjc/HalfCheetah-v4-ppo_fix_continuous_action-seed2/raw/main/poetry.lock
48
  poetry install --all-extras
49
+ python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id HalfCheetah-v4 --seed 2 --track
50
  ```
51
 
52
  # Hyperparameters
 
74
  'seed': 2,
75
  'target_kl': None,
76
  'torch_deterministic': True,
77
+ 'total_timesteps': 1000000,
78
+ 'track': True,
79
  'update_epochs': 10,
80
  'upload_model': True,
81
  'vf_coef': 0.5,
events.out.tfevents.1700810722.4090-171.1712170.0 → events.out.tfevents.1702935427.4090-171.242716.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:769688df25c8b28b8af7f1c8883bac366905d8d1d37e2fc3e72e894e673f3edd
3
- size 1519
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b0415c5b036980a987167a7055f8806f89b5c561741e8b8fde7298899f115d
3
+ size 376394
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
@@ -553,7 +553,7 @@ if __name__ == "__main__":
553
  model_path,
554
  make_eval_env,
555
  args.env_id,
556
- eval_episodes=1,
557
  run_name=f"{run_name}-eval",
558
  Model=Agent,
559
  device=device,
 
553
  model_path,
554
  make_eval_env,
555
  args.env_id,
556
+ eval_episodes=10,
557
  run_name=f"{run_name}-eval",
558
  Model=Agent,
559
  device=device,
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval/rl-video-episode-1.mp4 DELETED
Binary file (6.54 kB)
 
videos/{HalfCheetah-v4__ppo_fix_continuous_action__2__1700810722-eval → HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval}/rl-video-episode-0.mp4 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d465961060e38537833fb71e695a7f17a3fe31e390ebb29484c6604ca24214c
3
- size 3217333
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ff8568028087117e82b4a7c6141746d34506374f6f612b2f3101cd3ddd20c9
3
+ size 2037579
videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-1.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8be8fe5f9debe2828337c6cb72360d2f61252726db87bcc26c14fd70b18e0ae
3
+ size 2086772
videos/HalfCheetah-v4__ppo_fix_continuous_action__2__1702935419-eval/rl-video-episode-8.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43e954d9cc8290cc6d76be2c7797a0f66b9fb9f5ecd8581bcbd4fb35faf4170
3
+ size 2157054