Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 291.60 +/- 14.59
+      value: 287.58 +/- 13.30
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7dbc4684047cbf740a92d1597e8fc7edd7048318d45d97a43652d5fe1704d0
+oid sha256:1dc2a7b09db643f59260dce1a0cde66a569c6aafcb741b68a706cbc855e67e7d
 size 148171

results.json

@@ -1 +1 @@
-{"mean_reward": 291.6010890917289, "std_reward": 14.585126530603246, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T02:48:42.702923"}
+{"mean_reward": 287.57597177024974, "std_reward": 13.295295891976942, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-07T02:50:16.434347"}