PPO LunarLander-v2 trained agent

PPO_84.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f66a36c694b7309c1b321eace75ef1aaf97832f7fe97d704fa691c48034807
+oid sha256:76e2dee439c92336ccec03c4129a75b57446a2ea2bebf57f7f42ef6c58f7ef06
 size 150461

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 290.99 +/- 22.41
+      value: 301.34 +/- 16.08
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 290.9931485, "std_reward": 22.406182366987117, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:12:13.095690"}
+{"mean_reward": 301.3447673, "std_reward": 16.077276163310508, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:12:41.350936"}