Properly Trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 287.18 +/- 26.44
+      value: 288.93 +/- 19.72
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e724cdac9b99623c91de08b4dbcb7be12b1f58ba4c07cd4c5877dccffb2ac6d7
+oid sha256:17a0847c9b7af2b88398e320cbd55f0f399316aa9213f94c63286edb1da07301
 size 147222

results.json

@@ -1 +1 @@
-{"mean_reward": 287.18253425061664, "std_reward": 26.4408226580204, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T06:55:34.733299"}
+{"mean_reward": 288.9331599945202, "std_reward": 19.717999533644537, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-13T06:57:20.270369"}