pushing model

.gitattributes

@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__2__1702930540-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__2__1704457943-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__2__1704457943-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Walker2d-v4
     metrics:
     - type: mean_reward
-      value: 3415.35 +/- 1633.96
+      value: 3527.87 +/- 1758.34
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702930553.4090-171.189153.0 → events.out.tfevents.1704457952.4090-171.132877.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727fc9f06920fbcbba566bbb5ee96e4916effce2d3d335f636518141f3c193e1
+oid sha256:a1546b58c3d25740cd11d3bcb466c32b9dd278ca7d4f4ec80d1c765f9b19289d
 size 552953

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/{Walker2d-v4__ppo_fix_continuous_action__2__1702930540-eval → Walker2d-v4__ppo_fix_continuous_action__2__1704457943-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58cf3c084fa6da76a6557aacaa4914c09d47fb734a79866d018c72c64cce783
-size 1379514
+oid sha256:6785910c87024c07881a5be87f751170e8ebe0bc9e8d50b3ff45c4a6e50a1220
+size 1418197

videos/Walker2d-v4__ppo_fix_continuous_action__2__1704457943-eval/rl-video-episode-8.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f9fc6c60ffdac2cea20367ac2fba296f29ad082625c4aa350947fbd37b7c48
+size 1004926