Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 243.95 +/- 17.15
+      value: 223.97 +/- 69.23
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab73e75611a0d0812658308dcc807f309bc16cb12411ba56f9403ace5b665ba1
+oid sha256:5b819c46a32478728658ce85025f464d8655a9728149fd636067b9fcfd6e259f
 size 149574

results.json

@@ -1 +1 @@
-{"mean_reward": 243.95107912828152, "std_reward": 17.152785205862205, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T21:55:02.138674"}
+{"mean_reward": 223.96513855645622, "std_reward": 69.23098541471184, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-27T21:58:59.105756"}