Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 246.55 +/- 47.99
+      value: 248.97 +/- 19.79
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d6108c2bd251bd22a20c9915c29e549a12210f3c74271244bb5d0359338baf
+oid sha256:4c85ebdd752f5b160cadbc19c93592285db4d78755b9081a0114aeba0fee0e30
 size 149603

results.json

@@ -1 +1 @@
-{"mean_reward": 246.54962729999997, "std_reward": 47.99327117468416, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-06-30T02:50:00.544912"}
+{"mean_reward": 248.96578129999997, "std_reward": 19.792770069422936, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-06-30T02:50:23.418781"}