pushing model

.gitattributes

@@ -37,3 +37,6 @@ videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval/rl-video-ep
 videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
 replay.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: HalfCheetah-v4
     metrics:
     - type: mean_reward
-      value: 1636.48 +/- 11.27
+      value: 1640.51 +/- 33.40
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702935616.4090-171.247025.0 → events.out.tfevents.1704463487.4090-171.161713.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68a90c2f6933c56e324f6bbd1b410ffced6642a0a74d143904d7b7d28491b26a
+oid sha256:6b45cde0003c0d7c51c38416698b047ed434759ec86f9c9d8b2b37c2bc2b1468
 size 376394

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:c2d4bb11d2f92e00b5038e07c51dc59085accee7fd4179d38117dfe84785be86
-size 2020627
+oid sha256:5ef772844b50ee96d27a6886884667389061d311e1c6a35ee22f9ae086fa65ad
+size 2058420

videos/{HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval → HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval}/rl-video-episode-0.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa2ebd338824bee0e92c013518e13ec90066c2bdfbd6f6528646a4276dde5df
-size 2012444
+oid sha256:67ebe612727bac1af4c3ab8817b0e2ebc24f6771945a415b2900728448719ef1
+size 2015752

videos/{HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval → HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8bcd5e574a03d7f72204c56700499f7a3d5ebfc004ff9a1e42d20adc41d757
-size 1998690
+oid sha256:45f277c2ec1a3d4956f68d18cb76b8904e5544dce29897d1c5660033f27a0e59
+size 2022201

videos/{HalfCheetah-v4__ppo_fix_continuous_action__5__1702935608-eval → HalfCheetah-v4__ppo_fix_continuous_action__5__1704463477-eval}/rl-video-episode-8.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d4bb11d2f92e00b5038e07c51dc59085accee7fd4179d38117dfe84785be86
-size 2020627
+oid sha256:5ef772844b50ee96d27a6886884667389061d311e1c6a35ee22f9ae086fa65ad
+size 2058420