A cool PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 283.89 +/- 21.80
+      value: 287.31 +/- 15.83
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d343bf15cc9a020405a0287bb4b94884d290c627ad20e89468dff7d19cee62d
+oid sha256:f568236f8ad4d0e8cdc9566ebaafa2822d5b9b8590da66b66f43e504c8ec9b6b
 size 147432

results.json

@@ -1 +1 @@
-{"mean_reward": 283.89449634662054, "std_reward": 21.80266531498747, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-02T18:05:39.515982"}
+{"mean_reward": 287.30888371146233, "std_reward": 15.83084153659553, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-02T18:06:19.440301"}