train RL Agent for Lunar Lander environment

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 281.52 +/- 16.29
+      value: 289.98 +/- 12.62
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b89b91dc4018306014f5fdbf49f8617ceddddfe06742a368685477ab0fc4e3
+oid sha256:44430842dab9705fd6a816ffd6c49be499a770ab0394d0822c5fd2a8b9641b44
 size 147090

results.json

@@ -1 +1 @@
-{"mean_reward": 281.5178558177664, "std_reward": 16.29267485820377, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T16:54:24.064147"}
+{"mean_reward": 289.98059729238304, "std_reward": 12.61605677087679, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-12-20T16:55:01.591795"}