pushing model

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__1__1704452497-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__1__1704452497-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Hopper-v4
     metrics:
     - type: mean_reward
-      value: 2121.59 +/- 627.16
+      value: 2241.42 +/- 750.30
       name: mean_reward
       verified: false
 ---
@@ -46,7 +46,7 @@ curl -OL https://huggingface.co/sdpkjc/Hopper-v4-ppo_fix_continuous_action-seed1
 curl -OL https://huggingface.co/sdpkjc/Hopper-v4-ppo_fix_continuous_action-seed1/raw/main/pyproject.toml
 curl -OL https://huggingface.co/sdpkjc/Hopper-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 Hopper-v4
+python ppo_fix_continuous_action.py --save-model --upload-model --hf-entity sdpkjc --env-id Hopper-v4 --seed 1 --track
 ```
 
 # Hyperparameters

events.out.tfevents.1700813937.4090-171.1715316.0 → events.out.tfevents.1704452504.4090-171.104622.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499524d55328b12d9ee03ac9a2e3b14bb0dbd0900ee50c9493ff73b46c308b70
+oid sha256:5703a2b1b911a302d78cc874f8d5071bd6ebd1690dc77ac5a87cca06e27e8e66
 size 532071

ppo_fix_continuous_action.py

@@ -430,7 +430,7 @@ if __name__ == "__main__":
 
             # https://github.com/DLR-RM/stable-baselines3/pull/658
             for idx, trunc in enumerate(truncations):
-                if trunc:
+                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]

videos/Hopper-v4__ppo_fix_continuous_action__1__1704452497-eval/rl-video-episode-0.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7e775260f7254cacb9234f1f77bac3015edf865d6b72b7080b1aee1155bae5
+size 1375577

videos/Hopper-v4__ppo_fix_continuous_action__1__1704452497-eval/rl-video-episode-1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e162e3cf78d23500904a3c91115882d7a3437e440e9a217bfaf5140ffbcc61f8
+size 1289858