Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 269.11 +/- 14.54
+      value: 261.95 +/- 15.45
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4c7a6524ad540879bb40cbb4abffe584d41be824823e31cc60f9552179f459
+oid sha256:f2883f6755f8c5f6eb810d30380cd87b94aa34be6700a379afb0ace046512edc
 size 147153

results.json

@@ -1 +1 @@
-{"mean_reward": 269.1068071324118, "std_reward": 14.542901114826432, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-14T11:20:11.227684"}
+{"mean_reward": 261.9475571057929, "std_reward": 15.447169335129653, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-14T11:23:24.973394"}