pushing model

.gitattributes

@@ -37,3 +37,5 @@ videos/Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval/rl-video-episo
 videos/Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__5__1704458010-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__5__1704458010-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Walker2d-v4
     metrics:
     - type: mean_reward
-      value: 4443.28 +/- 1592.17
+      value: 3676.81 +/- 2029.78
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702930707.4090-171.191642.0 → events.out.tfevents.1704458017.4090-171.134192.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb1eae708ff751bdbe937b9606bf15c81bb480416b874ebec3ebeec8bf42dc7e
+oid sha256:d29ad978e4b715de2824d1d160af395758004fc8033aa653a25acc9d8852dc77
 size 573863

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 sha256:24b01d0c38835f09beca72abf1b97026988b7b2ff574d5ed11a3e0dfdc638d4c
-size 1336467
+oid sha256:f61c4498049be6699667b8f2dcfce01e341f59470175bf80a75f34748591eb91
+size 1342552

videos/Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval/rl-video-episode-1.mp4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e2a85fb8f1b0fb8ce35769a91996d87694588fa2f4a12fca91535975c2c3a54
-size 1341238

videos/{Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval → Walker2d-v4__ppo_fix_continuous_action__5__1704458010-eval}/rl-video-episode-0.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8e91113da13cc9097200019f773c1d97b2a405de245778a8033c90537a558f
-size 1309762
+oid sha256:0025ff0c0bf1e3a9e00e02613fb5e8bdb112ac68d1145c918eb4afaba6069fac
+size 1317485

videos/{Walker2d-v4__ppo_fix_continuous_action__5__1702930699-eval → Walker2d-v4__ppo_fix_continuous_action__5__1704458010-eval}/rl-video-episode-8.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b01d0c38835f09beca72abf1b97026988b7b2ff574d5ed11a3e0dfdc638d4c
-size 1336467
+oid sha256:f61c4498049be6699667b8f2dcfce01e341f59470175bf80a75f34748591eb91
+size 1342552