Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 244.31 +/- 17.58
+      value: 239.07 +/- 15.99
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17409d746dd4763e2d2cbd71e4429881f5716a9ef6c518e491eff3912360a4e
+oid sha256:4237cd3bd868d2670044ad28934056b5dc9391eda87c7485ea7c168674bdb42c
 size 150015

results.json

@@ -1 +1 @@
-{"mean_reward": 244.30937969999997, "std_reward": 17.579322320214363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T13:16:48.797799"}
+{"mean_reward": 239.0661706076988, "std_reward": 15.992398182720375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-05T13:23:39.999256"}