Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 268.12 +/- 16.22
+      value: 273.06 +/- 19.49
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bdd0912f7e6841293dbe02180db83e833160a35869f1cd201a96adc2d123ec0
+oid sha256:9c598a4140ad63e59fdeead1bbce8964ff30fe60e66c2b7dc6c2f9373d4c7b89
 size 149971

results.json

@@ -1 +1 @@
-{"mean_reward": 268.1207347, "std_reward": 16.220375456656093, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T12:19:39.040607"}
+{"mean_reward": 273.05922870000006, "std_reward": 19.493349036581108, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-31T12:20:49.815213"}