Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 290.51 +/- 20.06
+      value: 290.09 +/- 17.84
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587a712fb55bf1b76c471583d460faed238790b260c5dcd9e43ce8422716c4f6
+oid sha256:cdb0444bcb20cd470c2a00d19bd7e3e3b12fbca08bd884050f5f1731a4a2a2d0
 size 147173

results.json

@@ -1 +1 @@
-{"mean_reward": 290.5057408487225, "std_reward": 20.063278991850364, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-23T09:31:00.211613"}
+{"mean_reward": 290.08621500825416, "std_reward": 17.842668577766993, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-23T11:29:44.116168"}