pushing model

.gitattributes

@@ -37,3 +37,5 @@ videos/Ant-v4__ppo_fix_continuous_action__4__1702940478-eval/rl-video-episode-8.
 videos/Ant-v4__ppo_fix_continuous_action__4__1702940478-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Ant-v4__ppo_fix_continuous_action__4__1702940478-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Ant-v4__ppo_fix_continuous_action__4__1704452176-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Ant-v4__ppo_fix_continuous_action__4__1704452176-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Ant-v4
     metrics:
     - type: mean_reward
-      value: 3268.25 +/- 766.84
+      value: 2627.40 +/- 1335.96
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702940486.4090-171.302981.0 → events.out.tfevents.1704452190.4090-171.100802.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16100db8db230aa9c603a01bbb0784cfab0676d77145b433690ee5f75b73eef9
+oid sha256:fedc4da70e7b0b899162790c0a7070681c9afff3d11d447326f549d9e8c8b261
 size 739638

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]

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f24d8b6b37c132fc94f2ab65c12269936c8b08be5b0087ac69a47ef2861d63b1
-size 1796646
+oid sha256:3730087c1115830c6b37b0856faf3ecb8df232abcf58861241eab982a6c58181
+size 1292225

videos/Ant-v4__ppo_fix_continuous_action__4__1702940478-eval/rl-video-episode-0.mp4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f38608dd0b73fcb0a1f32331aeb542818ed6b6a2a2eced0c9413fdbbe1622a5f
-size 1737315

videos/{Ant-v4__ppo_fix_continuous_action__4__1702940478-eval → Ant-v4__ppo_fix_continuous_action__4__1704452176-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f535960988e582328d4168bcbda08bbc0803d4f13c997fa79639631957f4e2
-size 1840358
+oid sha256:e8ef159859cd6df8e1c1f7f7ff34cc6552a9cbf398a398c567535eff710d4324
+size 1834874

videos/{Ant-v4__ppo_fix_continuous_action__4__1702940478-eval → Ant-v4__ppo_fix_continuous_action__4__1704452176-eval}/rl-video-episode-8.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f24d8b6b37c132fc94f2ab65c12269936c8b08be5b0087ac69a47ef2861d63b1
-size 1796646
+oid sha256:3730087c1115830c6b37b0856faf3ecb8df232abcf58861241eab982a6c58181
+size 1292225