pushing model

.gitattributes

@@ -35,3 +35,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__3__1702930546-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
 videos/Walker2d-v4__ppo_fix_continuous_action__3__1702930546-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval/rl-video-episode-8.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval/rl-video-episode-1.mp4 filter=lfs diff=lfs merge=lfs -text
+videos/Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval/rl-video-episode-0.mp4 filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Walker2d-v4
     metrics:
     - type: mean_reward
-      value: 3181.49 +/- 1016.10
+      value: 3182.06 +/- 1431.00
       name: mean_reward
       verified: false
 ---

events.out.tfevents.1702930554.4090-171.189394.0 → events.out.tfevents.1704457952.4090-171.132942.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cc170280ec498049470cbe3660d57a91ca5993ae2c940fb366137e0526bdcf
+oid sha256:5b5e462f0803a153fe082250a4396b3aa20a9aa2fd1a8c7c863af84651a93984
 size 654893

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]

videos/{Walker2d-v4__ppo_fix_continuous_action__3__1702930546-eval → Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval}/rl-video-episode-0.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb66f3569332970a7d6d28b36fd159232d8aff308a6c8bd355b4b628cfb6bdbc
-size 1062037
+oid sha256:71d61f77f7ef29c16e619314507c069fb5fd83ef8a98f7737d0f4e889f23dc3d
+size 1379167

videos/{Walker2d-v4__ppo_fix_continuous_action__3__1702930546-eval → Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval}/rl-video-episode-1.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8c9bdd3b78a566b8f93a692c86dde85550835ba96b4945beb4b6b53ba7cafa
-size 1394379
+oid sha256:b7f45c5c7c89c0d3a9b24dfb340aa5a484c4fc36a3b098a8a072287172ab38a9
+size 1405556

videos/Walker2d-v4__ppo_fix_continuous_action__3__1704457944-eval/rl-video-episode-8.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:109226da2e759cf5a0f94897e14106343946f52d5ffbc97532d382f655b60d5a
+size 1401621