pushing model

.gitattributes

@@ -37,3 +37,4 @@ videos/Hopper-v4__ppo_fix_continuous_action__2__1702924579-eval/rl-video-episode
 videos/Hopper-v4__ppo_fix_continuous_action__2__1702924579-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Hopper-v4__ppo_fix_continuous_action__2__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__2__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: 2924.05 +/- 785.70
+      value: 2326.99 +/- 946.88
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702924587.4090-171.159907.0 → events.out.tfevents.1704452503.4090-171.104625.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d0054ec15b89db67a032d65bdbb29b270048dc774b1150793fecb6616fed205
-size 545435
+oid sha256:79c40584543324c3cc284f739b411d5148977bf797f133a501ea136ba37d989a
+size 540723

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:be470c9a8ee0d6b57cfefe68caf86cc1a986e7eeee7ef87e85dda1e9f7d303ab
-size 1464772
+oid sha256:0d3f4b7e56ba42a8787c687ecc3dec7156bb0bfe9eb23190f9e479463613d53b
+size 548765

videos/Hopper-v4__ppo_fix_continuous_action__2__1702924579-eval/rl-video-episode-1.mp4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:db58a52f4579bcaad5e27c65f61303fb63f2132a7e4e43d6a0223f92ef6a954b
-size 1587869

videos/Hopper-v4__ppo_fix_continuous_action__2__1702924579-eval/rl-video-episode-8.mp4

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be470c9a8ee0d6b57cfefe68caf86cc1a986e7eeee7ef87e85dda1e9f7d303ab
-size 1464772

videos/{Hopper-v4__ppo_fix_continuous_action__2__1702924579-eval → Hopper-v4__ppo_fix_continuous_action__2__1704452496-eval}/rl-video-episode-0.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467eaa8180b6bd2bc905cf7ad9e4a2cdfd8118e17833f9f8601b07a38ef783e2
-size 1575638
+oid sha256:5f579e7813de369907427962738e2abd4ebb797e97733cae0fdcd00275cc305e
+size 1573302