Upload PPO LunarLander-v3 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 237.38 +/- 21.00
+      value: 223.69 +/- 75.70
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60da0e3c8bb86064821ca20956d8279505a16f2a8bd92e0199aea7799a79bc16
+oid sha256:e46928037c7f80036985d7170c2284c4f4172ec0b9a569cb1690dee96a9dd634
 size 150021

results.json

@@ -1 +1 @@
-{"mean_reward": 237.3777486281055, "std_reward": 21.00445024537252, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-03T15:20:09.006073"}
+{"mean_reward": 223.69374723811157, "std_reward": 75.7017736154876, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-03T15:23:21.257382"}