Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 57.87 +/- 63.42
+      value: 0.26 +/- 54.20
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f3f0cd4566628c9c3f526b8e9dbd7e2cd722fb332fbd7cbb7b5b3b42ff328e
+oid sha256:1aa035ed885a74744996ec778761bb3d0ecf95c05b79a21534816c067aaf8d10
 size 146495

results.json

@@ -1 +1 @@
-{"mean_reward": 57.87221985871438, "std_reward": 63.417328563477454, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-18T09:34:54.115810"}
+{"mean_reward": 0.2582158365214127, "std_reward": 54.200598404574095, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-11-18T09:36:30.959653"}