Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 252.10 +/- 20.84
+      value: 231.24 +/- 74.44
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807d29f92dcc19ea042d1107826283c7d666b28b9326b0e8657f03c02761bd6e
+oid sha256:90e3a0a8b45c8ed26913a2fcc53fb93b8b56e65e88b2315d0b37c718777be362
 size 150355

results.json

@@ -1 +1 @@
-{"mean_reward": 252.09991225558997, "std_reward": 20.844945738209812, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-08-24T13:07:25.192762"}
+{"mean_reward": 231.2431025461919, "std_reward": 74.4425046324669, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-08-24T13:08:42.282011"}