PPO LunarLander-v2 trained agent

PPO_84.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38c2c293066b1a2aee290d461c9f914686364e5ef8ffc4772954c5d813470d4
+oid sha256:80f66a36c694b7309c1b321eace75ef1aaf97832f7fe97d704fa691c48034807
 size 150461

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 289.34 +/- 17.95
+      value: 290.99 +/- 22.41
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 289.3407893, "std_reward": 17.94723441207917, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:11:55.349632"}
+{"mean_reward": 290.9931485, "std_reward": 22.406182366987117, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:12:13.095690"}