Unit 1 - Lunar PPO

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 284.82 +/- 25.72
+      value: 294.73 +/- 14.50
       name: mean_reward
       verified: false
 ---

ppo_lunar_agent_3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4203046cf42f3e5c74aa732072a0fb80bab41fd442ae3a08cfcc041618245c0f
+oid sha256:5d7be2e71f26ed5eb85cf8d3944d57b665a14e2047891593048c28c4c61350b5
 size 147823

results.json

@@ -1 +1 @@
-{"mean_reward": 284.81753423830264, "std_reward": 25.72149871520299, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T09:05:50.036677"}
+{"mean_reward": 294.73078786029504, "std_reward": 14.501977693798445, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T09:06:55.774865"}