Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 267.26 +/- 21.63
+      value: 247.43 +/- 39.05
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d1333162c5e82743bbf01965d4d8022a5003d74547016ff695901d436f9856
+oid sha256:7fb87c8deb7e276ff3b06d3a24900af90b5ebf573c63f57ed847178626b2f0e5
 size 147987

results.json

@@ -1 +1 @@
-{"mean_reward": 267.2624795, "std_reward": 21.63472795383452, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-04T20:08:58.590740"}
+{"mean_reward": 247.43048012268864, "std_reward": 39.046860537595, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-09-04T20:20:14.685029"}