LunarLandar using PPO

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 255.68 +/- 39.22
+      value: 279.31 +/- 11.46
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 255.68160070000005, "std_reward": 39.22429799551327, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-23T10:57:51.807123"}
+{"mean_reward": 279.31298449999997, "std_reward": 11.463603999671383, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-07-23T10:59:33.329662"}

sar-lunarlandar-moon-ppo.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59ec478ae0fda36489b61803a317bdba7fedeb04a47f641f7bef9dd4e975c09b
+oid sha256:0a44c2afc4392b3e72a3253f94ec37e2afc978c8ecce1f7288a065dbaa49b8b9
 size 146745