train RL Agent for Lunar Lander environment

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 290.25 +/- 21.03
+      value: 290.30 +/- 19.57
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdcbaa3f88150a01e6587d628c2c3825c717c4121d88708a0e03e1a0f92f497
+oid sha256:ef91fe9491622a3b41845a457efdca269ce29b58009ec18680af563267ad1452
 size 147090

results.json

@@ -1 +1 @@
-{"mean_reward": 290.25071758996046, "std_reward": 21.0297771627313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T16:49:23.721647"}
+{"mean_reward": 290.30465761812496, "std_reward": 19.567545288553966, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T16:50:14.599870"}