first training of the lunar landar with ppo

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 265.06 +/- 19.59
+      value: 265.62 +/- 23.35
       name: mean_reward
       verified: false
 ---

ppo-lunarlander-v2-smartpants.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef1f2232fc00133bd723f9931e7220c5dd010452e0aa0755d7ab42250c74a55
+oid sha256:c772ef75ade2b156fe6e91fd28873fd1ab88a921e6367770a58e880fe97b02cb
 size 146742

results.json

@@ -1 +1 @@
-{"mean_reward": 265.06020939999996, "std_reward": 19.588351437623995, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-25T14:51:17.531084"}
+{"mean_reward": 265.6175529, "std_reward": 23.346565690508776, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-25T14:52:36.943098"}