Upload baseline PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.79 +/- 12.29
+      value: 258.98 +/- 18.52
       name: mean_reward
       verified: false
 ---

lunarlander-v2_ppo_v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78c8324a6321daf310e5a512b5084ed4c8c69c4b03d2a3b144c54abd95e6e52
+oid sha256:aab81624293858438b755b36b0f3c4ca5bc9349674bf068a7b1839215beefd9b
 size 145917

results.json

@@ -1 +1 @@
-{"mean_reward": 247.79293876379307, "std_reward": 12.291194859734047, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-15T14:13:00.010466"}
+{"mean_reward": 258.98265062935377, "std_reward": 18.51602437736822, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-15T14:14:48.100705"}