Unit 1 - Lunar PPO

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 286.22 +/- 17.34
+      value: 303.73 +/- 10.36
       name: mean_reward
       verified: false
 ---

ppo_lunar_agent_3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7dcd9b41f9da7452e67970dddc14f7121159fe06226a2fa0f07797b022bbbe9
+oid sha256:aa59e889aaf5e768ac8f01620603da19b742ca2cb3d22fbad05bb1cbf0232eed
 size 147823

results.json

@@ -1 +1 @@
-{"mean_reward": 286.2229017513525, "std_reward": 17.336939125696247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T09:09:11.887637"}
+{"mean_reward": 303.7302065446468, "std_reward": 10.355763678851714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-02T09:09:39.717529"}