Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 146.86 +/- 42.15
+      value: 109.38 +/- 95.91
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581031644e2368593080c6261e0eb52af0969ce3a9b3006a1a26a1a8ea08f291
+oid sha256:afff257c37cab4340748edeb7bde313a366a0d1417a9a5c1ebee00281052f0a1
 size 147136

results.json

@@ -1 +1 @@
-{"mean_reward": 146.86443082339207, "std_reward": 42.150108695750156, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-26T11:30:30.325325"}
+{"mean_reward": 109.3750551340858, "std_reward": 95.90782009922142, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-26T11:59:18.554462"}