Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 250.81 +/- 24.26
+      value: 260.68 +/- 22.20
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250dabc44b4598866de500feb0fd00cf6e68e2f9db582b5e3586bf29ad3de5f3
+oid sha256:e168d9f4fa22815d76ba80a516ae1aeb8bdbe47b4a1a9a19d9748a0bc98950a0
 size 148094

results.json

@@ -1 +1 @@
-{"mean_reward": 250.8087594, "std_reward": 24.26280989868249, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-30T20:00:28.050912"}
+{"mean_reward": 260.6778334, "std_reward": 22.19858138704235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-30T20:08:53.962887"}