Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 240.01 +/- 13.93
+      value: 232.91 +/- 17.70
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb9e217fa425547bc421d7bb78b811fe8536b19c48e5030ae5585b3d51498b6
+oid sha256:8213e4e1cd6841360a82084ed50afce67bff4234d0d4bad1c169b1e72bf2f587
 size 150007

results.json

@@ -1 +1 @@
-{"mean_reward": 240.0080301376833, "std_reward": 13.925544066980857, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-18T16:32:29.711784"}
+{"mean_reward": 232.91162073130917, "std_reward": 17.699788118296166, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-18T16:36:29.755269"}