Retrain PPO model for BipedalWalker-v3 v2

PPO-BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d4eb3cacd473dcba1411c9a2e10f0c251afa32e53c38892337dcec79113420
+oid sha256:56098457211a0f230d995b08614c1e07d3d0e425f0139f9620c529cfa4d8d68a
 size 174004

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 292.80 +/- 30.97
+      value: 303.47 +/- 1.90
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1fc634d35b83f9f9b9fc59f671d58b45d3fb0636f2de2f688b8bb04db0cb292
-size 450565
+oid sha256:74955739e802ef45416a1b9c4c217b3c475d4b56221e35c20e6a80243b2539a7
+size 443267

results.json

@@ -1 +1 @@
-{"mean_reward": 292.7973056465179, "std_reward": 30.97333848848356, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T16:40:26.692642"}
+{"mean_reward": 303.47284860582147, "std_reward": 1.9019684625377884, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-13T16:46:01.911994"}