PPO LunarLander-v2 trained agent

PPO_89.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06dc131d55ad5b43bf099c1808092f7c7a3e965f3665199161f1f20887c19dd5
+oid sha256:b6f063f3ae4eb3a375852616274c6285b389f11c27cf77f1514c1de2e0ff6e74
 size 152858

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 283.54 +/- 17.81
+      value: 280.14 +/- 17.02
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 283.53779849999995, "std_reward": 17.8117678525987, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:01:10.168030"}
+{"mean_reward": 280.1437801, "std_reward": 17.01612686757744, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T15:01:24.981869"}