pushing model

.gitattributes

@@ -37,3 +37,5 @@ videos/Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval/rl-video-episode
 videos/Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__4__1704452496-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__4__1704452496-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Hopper-v4
     metrics:
     - type: mean_reward
-      value: 3509.01 +/- 327.98
+      value: 3220.86 +/- 688.15
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702924586.4090-171.159912.0 → events.out.tfevents.1704452503.4090-171.104630.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a6ea8b2810b4317ceca09635a92bc3cc0794a295c6d5d53f50ea4a86ffbd97
+oid sha256:718f46dc88f935f62ebb204ccc1f28fe00ff6439b13105de2fbd8df00136850d
 size 517443

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:e8ae14a7517aa81bb36a4f79d3ff1b60e590831e29587485e67d0334309e0276
-size 1435253
+oid sha256:a1cfd61c8162dc544a41ba35906fcb7c0326d62280eebf20fb7e48d6c18d164d
+size 1511663

videos/Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval/rl-video-episode-0.mp4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7e3e14f417633c28e71267f9faea4389e97d3ee3d125d8bb703778470e4196cd
-size 1546767

videos/{Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval → Hopper-v4__ppo_fix_continuous_action__4__1704452496-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb36d3193c048f77a2d7adf7b97a905b7da23ec9f8a10ff90cee7d4aba08b3a4
-size 1485668
+oid sha256:c04dc577bcd60edd71834a4908e587b63aa22dc438e67f05afd9fe411d86398d
+size 1347230

videos/{Hopper-v4__ppo_fix_continuous_action__4__1702924579-eval → Hopper-v4__ppo_fix_continuous_action__4__1704452496-eval}/rl-video-episode-8.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ae14a7517aa81bb36a4f79d3ff1b60e590831e29587485e67d0334309e0276
-size 1435253
+oid sha256:a1cfd61c8162dc544a41ba35906fcb7c0326d62280eebf20fb7e48d6c18d164d
+size 1511663