Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 268.15 +/- 14.61
+      value: 260.49 +/- 21.11
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2-10env-1E6step.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5bba878aaa130711235bbc5d4d5accd054867e24e1e10f51e969d4c9ac9bff
+oid sha256:50f659caabbc5d960789ac255f3b8d3fb745d33ad5682a691063c823693a2e5c
 size 146124

results.json

@@ -1 +1 @@
-{"mean_reward": 268.1537709375685, "std_reward": 14.605803732213335, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-25T18:57:37.864390"}
+{"mean_reward": 260.48588053535315, "std_reward": 21.10809865992554, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-25T19:14:13.508053"}