sdpkjc commited on
Commit
389150c
1 Parent(s): 11abbde

pushing model

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: Swimmer-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 124.70 +/- 1.56
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/Swimmer-v4-ppo_fix_continuous_action-seed
46
  curl -OL https://huggingface.co/sdpkjc/Swimmer-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/sdpkjc/Swimmer-v4-ppo_fix_continuous_action-seed1/raw/main/poetry.lock
48
  poetry install --all-extras
49
- python ppo_fix_continuous_action.py --save-model --hf-entity sdpkjc --seed 1 --upload-model --track --env-id Swimmer-v4
50
  ```
51
 
52
  # Hyperparameters
 
16
  type: Swimmer-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 124.05 +/- 2.58
20
  name: mean_reward
21
  verified: false
22
  ---
 
46
  curl -OL https://huggingface.co/sdpkjc/Swimmer-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
47
  curl -OL https://huggingface.co/sdpkjc/Swimmer-v4-ppo_fix_continuous_action-seed1/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 Swimmer-v4 --seed 1 --track
50
  ```
51
 
52
  # Hyperparameters
events.out.tfevents.1700813954.4090-171.1716227.0 → events.out.tfevents.1704457676.4090-171.127219.0 RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5a2e881d890ddec39b87458115a8a1ff9d2c97eb90579eff8e19c390ddfb09
3
  size 376390
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a6923c2e8c876db8656fa0ff57440c0edfe325041e98489c0396ce72f6aeb2c
3
  size 376390
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/Swimmer-v4__ppo_fix_continuous_action__1__1700813947-eval/rl-video-episode-0.mp4 DELETED
Binary file (847 kB)
 
videos/Swimmer-v4__ppo_fix_continuous_action__1__1700813947-eval/rl-video-episode-1.mp4 DELETED
Binary file (853 kB)
 
videos/Swimmer-v4__ppo_fix_continuous_action__1__1700813947-eval/rl-video-episode-8.mp4 DELETED
Binary file (849 kB)
 
videos/Swimmer-v4__ppo_fix_continuous_action__1__1704457667-eval/rl-video-episode-0.mp4 ADDED
Binary file (849 kB). View file
 
videos/Swimmer-v4__ppo_fix_continuous_action__1__1704457667-eval/rl-video-episode-1.mp4 ADDED
Binary file (858 kB). View file
 
videos/Swimmer-v4__ppo_fix_continuous_action__1__1704457667-eval/rl-video-episode-8.mp4 ADDED
Binary file (852 kB). View file