Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 297.71 +/- 21.99
+      value: 294.70 +/- 17.14
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714934c691f5158f3677a9e5556ebd09a34a66a2ff8a2f01f09df43606c0ab5b
+oid sha256:c18eb717f52f912b4b07425f321a8d95cda292aff73cff4013128a8fab29b9ab
 size 149251

results.json

@@ -1 +1 @@
-{"mean_reward": 297.7099634051328, "std_reward": 21.990166769975094, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-20T12:28:57.051886"}
+{"mean_reward": 294.69630161632864, "std_reward": 17.139018447549248, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-20T12:29:41.641888"}