Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 209.69 +/- 86.94
+      value: 253.38 +/- 17.60
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc0938ee64ed8a30b9a76aa21379d45ab05709402af008597af4fbb53cd0fb6
+oid sha256:4da4e25a357b1da6cc0586e6984933ae913dc6c2ddf2bc325cc8f2c39a5f3831
 size 150294

results.json

@@ -1 +1 @@
-{"mean_reward": 209.68723529999997, "std_reward": 86.94128366418802, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-16T23:59:09.288014"}
+{"mean_reward": 253.3847473, "std_reward": 17.595122292731997, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-12-17T00:02:45.582966"}