Add model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 223.90 +/- 19.04
+      value: 225.80 +/- 22.10
       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:e1e7edc945a4c5f81af988b0ae6b4dd3ab19c2e81a1e75c27c2bc3f6c6b7f9ad
+oid sha256:31455dadd3ae381709a7da3b6fafe1e269b90e0f4cb3a182b39c8a07494afb11
 size 147144

results.json

@@ -1 +1 @@
-{"mean_reward": 223.90463360342397, "std_reward": 19.037096800579548, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T15:58:55.679946"}
+{"mean_reward": 225.80241671338908, "std_reward": 22.102053210680364, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T16:32:30.635104"}