Test Upload PPO BipedalWalker-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: BipedalWalker-v3
     metrics:
     - type: mean_reward
-      value: 197.93 +/- 13.70
+      value: -83.23 +/- 36.28
       name: mean_reward
       verified: false
 ---

ppo-BipedalWalker-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce7322a4b52221781e969a50e03b6da329421287a35b3269bde93992a526659
+oid sha256:6533ad738d125b8e8cc0aaf412cfdd4e87ab9496e9c58f70085408d9bf3df9fd
 size 174610

results.json

@@ -1 +1 @@
-{"mean_reward": 197.93299275676955, "std_reward": 13.69558453765639, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-24T16:40:05.158313"}
+{"mean_reward": -83.22893290474948, "std_reward": 36.28020398816584, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-24T16:42:05.580391"}