Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 251.95 +/- 19.62
+      value: 245.04 +/- 29.77
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342ec77a5e5b347a48327b4d17e3915ee8641a0311e75341c30afa9e8417579d
+oid sha256:b8398f6b88ce32fd7c8ef286c6c2ab7b5fbae35a6f5eaf7221fae8e716916526
 size 152590

results.json

@@ -1 +1 @@
-{"mean_reward": 251.95050758311504, "std_reward": 19.624703051175203, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-04T22:22:09.273540"}
+{"mean_reward": 245.04040283527848, "std_reward": 29.772422302657365, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-04T22:39:16.168282"}