pushing model

Browse files

Files changed (9) hide show

.gitattributes +4 -0
README.md +2 -2
events.out.tfevents.1700813944.4090-171.1715549.0 → events.out.tfevents.1704457900.4090-171.131845.0 +1 -1
ppo_fix_continuous_action.py +1 -1
replay.mp4 +0 -0
videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-8.mp4 +0 -0
videos/{Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval → Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval}/rl-video-episode-0.mp4 +2 -2
videos/{Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval → Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval}/rl-video-episode-1.mp4 +2 -2
videos/Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval/rl-video-episode-8.mp4 +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ model-index:
       type: Walker2d-v4
     metrics:
     - type: mean_reward
-      value: 4097.58 +/- 414.35
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-see
 curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed1/raw/main/poetry.lock
 poetry install --all-extras
-python ppo_fix_continuous_action.py --save-model --hf-entity sdpkjc --seed 1 --upload-model --track --env-id Walker2d-v4
 ```
 # Hyperparameters

       type: Walker2d-v4
     metrics:
     - type: mean_reward
+      value: 3572.02 +/- 949.89
       name: mean_reward
       verified: false
 ---
 curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/sdpkjc/Walker2d-v4-ppo_fix_continuous_action-seed1/raw/main/poetry.lock
 poetry install --all-extras
+python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Walker2d-v4 --seed 1 --track
 ```
 # Hyperparameters

events.out.tfevents.1700813944.4090-171.1715549.0 → events.out.tfevents.1704457900.4090-171.131845.0 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:075dadda3e83e6506c15f03bedd106e5fbcafe145398da2549b5b5d0fe5886c7
 size 603119

 version https://git-lfs.github.com/spec/v1
+oid sha256:6470277b8c9aebfb03fedad4fd81f03774143cf8098d2d287357402ba3c8b0ff
 size 603119

ppo_fix_continuous_action.py CHANGED Viewed

@@ -430,7 +430,7 @@ if __name__ == "__main__":
             # https://github.com/DLR-RM/stable-baselines3/pull/658
             for idx, trunc in enumerate(truncations):
-                if trunc:
                     real_next_obs = infos["final_observation"][idx]
                     with torch.no_grad():
                         terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]

             # https://github.com/DLR-RM/stable-baselines3/pull/658
             for idx, trunc in enumerate(truncations):
+                if trunc and not terminations[idx]:
                     real_next_obs = infos["final_observation"][idx]
                     with torch.no_grad():
                         terminal_value = agent.get_value(torch.Tensor(real_next_obs).to(device)).reshape(1, -1)[0][0]

replay.mp4 CHANGED Viewed

Binary files a/replay.mp4 and b/replay.mp4 differ

videos/Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval/rl-video-episode-8.mp4 DELETED Viewed

Binary file (928 kB)

videos/{Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval → Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval}/rl-video-episode-0.mp4 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc1bd9f7be317f1291a5c90f11683338f4e49e31ed4fd592f50345616614689c
-size 1369864

 version https://git-lfs.github.com/spec/v1
+oid sha256:355f07400d066816cb4a50465e37667bfed83aa39b3bcf61ed85d9cd988d32d4
+size 1361422

videos/{Walker2d-v4__ppo_fix_continuous_action__1__1700813937-eval → Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval}/rl-video-episode-1.mp4 RENAMED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372d5569046330756830d9f952cafdeaaad6f9b787b84ce02b9f8785acbd6af5
-size 1366648

 version https://git-lfs.github.com/spec/v1
+oid sha256:833c5f935b64f591e21299d3a2a585df61775af9acc326e3859dcce5860b552f
+size 1348943

videos/Walker2d-v4__ppo_fix_continuous_action__1__1704457892-eval/rl-video-episode-8.mp4 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e18eca4f5295d9e5060dec1c1681bece565b9df365cedb7ebc4998bea06ae9b
+size 1353396