pushing model

.gitattributes

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 videos/Hopper-v4__ppo_fix_continuous_action__3__1702924580-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Hopper-v4__ppo_fix_continuous_action__3__1702924580-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__3__1704452496-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__3__1704452496-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Hopper-v4__ppo_fix_continuous_action__3__1704452496-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: 2860.95 +/- 751.81
+      value: 3107.79 +/- 707.01
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702924587.4090-171.159911.0 → events.out.tfevents.1704452504.4090-171.104628.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e3ee61324962b9c26430069795491718af30cf47a8bb153a7faff07b7505c9
+oid sha256:55732f970316e5655cef59173c947ae42f9ffab369745f158da5fcec67646ff8
 size 581895

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:abbaeaacdea16bba8d08fbde9ad6f368969af2be11f8871b62da2f56c9f1e1da
-size 1603602
+oid sha256:8a96a0d11838a5af7baf5fbb4003920eaf41d38d41c50f138f74be1ca83ca92b
+size 1599247

videos/Hopper-v4__ppo_fix_continuous_action__3__1704452496-eval/rl-video-episode-0.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e7e4d713e3461fb80bca2fb44f713ebe4678a0e3e320f79bab03c53c69ca86
+size 1607748

videos/{Hopper-v4__ppo_fix_continuous_action__3__1702924580-eval → Hopper-v4__ppo_fix_continuous_action__3__1704452496-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4327bcb16139c146aaca0a3859dda5fa892019cfb718e4c11ddc28e4c39141
-size 1055468
+oid sha256:7a397b046786324f75063fae96652513a95455cc157039bf9af2eb3600530144
+size 1598407

videos/{Hopper-v4__ppo_fix_continuous_action__3__1702924580-eval → Hopper-v4__ppo_fix_continuous_action__3__1704452496-eval}/rl-video-episode-8.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abbaeaacdea16bba8d08fbde9ad6f368969af2be11f8871b62da2f56c9f1e1da
-size 1603602
+oid sha256:8a96a0d11838a5af7baf5fbb4003920eaf41d38d41c50f138f74be1ca83ca92b
+size 1599247