Second RL model

LunarLander_v2-PPO.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0bbb05cea8d9754bf030c0037a19eab4e97f2e6bc099315e042b7547c1d672c
+oid sha256:e41a3720c74abca2eca506ad0c2d08e2fcbb58418e385766ce5816762ad86f01
 size 146699

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 254.92 +/- 20.95
+      value: 256.48 +/- 14.46
       name: mean_reward
       verified: false
 ---

results.json

@@ -1 +1 @@
-{"mean_reward": 254.92429886034785, "std_reward": 20.945575573630375, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T11:21:20.862539"}
+{"mean_reward": 256.4828945631626, "std_reward": 14.462702546463465, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-07T11:23:52.925299"}