Upload PPO BipedalWalker-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: 5.26 +/- 87.88
+      value: -30.43 +/- 71.39
       name: mean_reward
       verified: false
 ---

ppo-BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef65c5e87691708cd5bc41e02eec018ba7c0d7ab528246b61daa58beb03dc2ea
+oid sha256:c8b7409c6c2224f7569df8f69f8d211ff4f01b0c3d87c66b73940fde9a39977e
 size 177653

results.json

@@ -1 +1 @@
-{"mean_reward": 5.26073571848101, "std_reward": 87.88194632807014, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-26T16:41:44.014496"}
+{"mean_reward": -30.429033508170686, "std_reward": 71.39365961768118, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-26T16:53:12.373342"}