Upload PPO LunarLander-v2 trained agent with 1mln steps

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -42.89 +/- 30.54
+      value: -80.59 +/- 42.60
       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:e9e43e96ec6f3ace5109cb8c9bcf9efe1426c9fbaa3d1b599e8a2c1574357111
+oid sha256:6a20221419c6a71569d1e45944db68225af9efc141f7b9f110c79881a7f8360a
 size 52885

results.json

@@ -1 +1 @@
-{"mean_reward": -42.89330002684146, "std_reward": 30.536615733546483, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T22:16:12.547078"}
+{"mean_reward": -80.59060994540341, "std_reward": 42.59550653898667, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T22:17:12.590261"}