Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 260.54 +/- 17.62
+      value: 267.05 +/- 13.81
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1896cab1bbe850cff7a5f2a76c177f889fc423b4ff1c13805a64ce67f672172c
+oid sha256:16eb4ec90048a4322fef46c4cd64712f52d1c1a199e13089b02b725eea36cd02
 size 148080

results.json

@@ -1 +1 @@
-{"mean_reward": 260.5370408, "std_reward": 17.6208645794315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T07:24:57.272399"}
+{"mean_reward": 267.0500300239305, "std_reward": 13.805122407887684, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-14T07:25:24.558448"}