Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 249.05 +/- 22.92
+      value: 250.07 +/- 19.30
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34fd7477b6fa303c5b4fd8ac9402f87df734eacf91afd364de12ad04dc23644
+oid sha256:5331bd3d3ebdd6efef15192586fb50c07264a81ecc4d060dde3549e6650e9618
 size 148068

results.json

@@ -1 +1 @@
-{"mean_reward": 249.04719313356236, "std_reward": 22.92414738472419, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-09T00:06:17.884546"}
+{"mean_reward": 250.0728512983423, "std_reward": 19.303933815254616, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-09T00:07:32.452414"}