Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 249.51 +/- 45.14
+      value: 241.10 +/- 46.82
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248a08eecaf66116331dc51dd148afe1f6fe650c88a22e5a4e62d4a06d6776f4
+oid sha256:387059ce0355dfe59eeb60071ec034c9a48bc12aebcf401c4db6ae101858b6c3
 size 149558

results.json

@@ -1 +1 @@
-{"mean_reward": 249.50935709292713, "std_reward": 45.142061609257695, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-21T09:01:12.400547"}
+{"mean_reward": 241.099177732717, "std_reward": 46.819208909586315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-21T09:12:20.039522"}