Upload PPO LunarLander-v2 trained agent

LunarLanderV2_PPO_Mlp_1M.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247b482aa385694cc240f51cd8ff9a2fb2a08135ce220a6aa8b1b19a92d85b85
+oid sha256:1dd4fe03b8c074fb7bb79b79752406e553a91791e1bec243d62bfec53f5ea864
 size 305912

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 269.54 +/- 19.35
+      value: 286.13 +/- 15.43
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 269.5409629, "std_reward": 19.35013669300486, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-23T09:41:54.867226"}
+{"mean_reward": 286.13151609999994, "std_reward": 15.430438086193973, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-23T10:17:48.252488"}