This is another Reinforsement Learning model I made via HuggingFace's course

BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26b48a45395b4fe77f93f3f49d7eacdd8763a237c40c87295edab5a781ac7b93
+oid sha256:ae9de8e7df59b927701215bbb750bffd28928d4d9328ba690225598eff5bc1f7
 size 181776

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: 301.60 +/- 34.36
+      value: 311.65 +/- 2.28
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa95bc731326bfb11821d56aaa79bc12369b4853dbc7d4401979826ac54daa0b
-size 4159351
+oid sha256:b140105473bffd9702c3f43338ed3225231acb1c3fdaa871d6cd2f123879666d
+size 471191

results.json

@@ -1 +1 @@
-{"mean_reward": 301.5954648118415, "std_reward": 34.359621472787126, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T03:35:52.206809"}
+{"mean_reward": 311.6512355959436, "std_reward": 2.2809537283807564, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-24T03:38:27.836073"}