Hugging Face's logo

qgallouedec
/
Hopper-v4-ppo_continuous_action-seed1

Reinforcement Learning
TensorBoard
cleanrl
Hopper-v4
deep-reinforcement-learning
custom-implementation
Eval Results
Model card Files Metrics Community
qgallouedec HF staff commited on
Commit
375894c
•
1 Parent(s): 3121818

pushing model

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. events.out.tfevents.1712439414.MacBook-Pro-de-Quentin.local.22067.0 → events.out.tfevents.1712439499.MacBook-Pro-de-Quentin.local.22168.0 +2 -2
  3. ppo_continuous_action.cleanrl_model +0 -0
  4. replay.mp4 +0 -0
  5. videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-0.mp4 +0 -0
  6. videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-1.mp4 +0 -0
  7. videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-8.mp4 +0 -0
  8. videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-0.mp4 +0 -0
  9. videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-1.mp4 +0 -0
  10. videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-8.mp4 +0 -0
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: Hopper-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 13.96 +/- 25.82
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/qgallouedec/Hopper-v4-ppo_continuous_action-seed
46
  curl -OL https://huggingface.co/qgallouedec/Hopper-v4-ppo_continuous_action-seed1/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/qgallouedec/Hopper-v4-ppo_continuous_action-seed1/raw/main/poetry.lock
48
  poetry install --all-extras
49
- python ppo_continuous_action.py --env-id Hopper-v4 --save-model --upload-model --hf-entity qgallouedec --total-timesteps 50000
50
  ```
51
 
52
  # Hyperparameters
@@ -74,7 +74,7 @@ python ppo_continuous_action.py --env-id Hopper-v4 --save-model --upload-model -
74
  'seed': 1,
75
  'target_kl': None,
76
  'torch_deterministic': True,
77
- 'total_timesteps': 50000,
78
  'track': False,
79
  'update_epochs': 10,
80
  'upload_model': True,
 
16
  type: Hopper-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 11.40 +/- 4.28
20
  name: mean_reward
21
  verified: false
22
  ---
 
46
  curl -OL https://huggingface.co/qgallouedec/Hopper-v4-ppo_continuous_action-seed1/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/qgallouedec/Hopper-v4-ppo_continuous_action-seed1/raw/main/poetry.lock
48
  poetry install --all-extras
49
+ python ppo_continuous_action.py --env-id Hopper-v4 --save-model --upload-model --hf-entity qgallouedec --total-timesteps 500000
50
  ```
51
 
52
  # Hyperparameters
 
74
  'seed': 1,
75
  'target_kl': None,
76
  'torch_deterministic': True,
77
+ 'total_timesteps': 500000,
78
  'track': False,
79
  'update_epochs': 10,
80
  'upload_model': True,
events.out.tfevents.1712439414.MacBook-Pro-de-Quentin.local.22067.0 → events.out.tfevents.1712439499.MacBook-Pro-de-Quentin.local.22168.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74ad1a5010d15a5034c35e9305d11ce83ee9ea6f2ae8dfc71313bf991575ca9e
3
- size 100295
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe2001e5c71fde816fd64ac8eea337fb796052e6eb9ba5666cd96b38e01565e
3
+ size 364878
ppo_continuous_action.cleanrl_model CHANGED
Binary files a/ppo_continuous_action.cleanrl_model and b/ppo_continuous_action.cleanrl_model differ
 
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-0.mp4 DELETED
Binary file (111 kB)
 
videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-1.mp4 DELETED
Binary file (33.3 kB)
 
videos/Hopper-v4__ppo_continuous_action__1__1712439414-eval/rl-video-episode-8.mp4 DELETED
Binary file (40 kB)
 
videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-0.mp4 ADDED
Binary file (44 kB). View file
 
videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-1.mp4 ADDED
Binary file (51.6 kB). View file
 
videos/Hopper-v4__ppo_continuous_action__1__1712439499-eval/rl-video-episode-8.mp4 ADDED
Binary file (39.9 kB). View file