PPO LunarLander-v2 trained agent

PPO_90.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2f7e9fcbc7555af360aa099603c529760413b237930906b3c7430eedba1560
+oid sha256:528fb5200595f51bf266cce455e13d73e24f496d7221b58ac79fe1fb1593a48e
 size 153027

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 276.40 +/- 21.26
+      value: 274.58 +/- 20.08
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 276.40272139999996, "std_reward": 21.26387457344501, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T14:54:26.839630"}
+{"mean_reward": 274.58223059999995, "std_reward": 20.07703509630583, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-19T14:54:41.903703"}