Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 200.53 +/- 92.64
+      value: 249.39 +/- 13.54
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0ff3fb3c2b019ecc3258e7b6fcca6ce12b9fbe64c099671de32253108605ad
+oid sha256:7ca07d41940863c40c9db210fd2639739d93aca5fd63d83a7a9a950e0d66b72e
 size 147426

results.json

@@ -1 +1 @@
-{"mean_reward": 200.5282352, "std_reward": 92.64317743209561, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-19T21:41:07.471474"}
+{"mean_reward": 249.3926499241757, "std_reward": 13.539930002088006, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-19T21:41:38.713996"}