Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 260.18 +/- 15.16
+      value: 254.84 +/- 9.82
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e507ff635e5a910587cd06a146172a250e7b80c77c54bff2bded9a7f32bfba
+oid sha256:6a4ae0d8d78f7e1cee45b8a62f5782ef1548a9e6ff3f8ec2c928e316fe91321a
 size 148048

results.json

@@ -1 +1 @@
-{"mean_reward": 260.1841845, "std_reward": 15.162424717044797, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T06:23:01.602874"}
+{"mean_reward": 254.8414116591989, "std_reward": 9.816717410456404, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T06:23:34.470308"}