Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 259.23 +/- 21.19
+      value: 275.37 +/- 23.18
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14c9fa49d939e253e886c18d6784fd87355170e4d15bdf5b4d9edeb94966c85b
+oid sha256:5421d56882a2ab24a12a1592701ede5b2822b6d99c989a1ae04ff2ff1e7af0cb
 size 149599

results.json

@@ -1 +1 @@
-{"mean_reward": 259.2265365748609, "std_reward": 21.18700984181981, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-07-25T15:51:48.890924"}
+{"mean_reward": 275.36739059683146, "std_reward": 23.18462887441104, "is_deterministic": true, "n_eval_episodes": 3, "eval_datetime": "2026-07-25T15:55:14.012892"}