first commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 296.31 +/- 13.37
+      value: 293.10 +/- 16.59
       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:a2a162b85d72124683f72286237c361441204e348c26f768f6cffdbe33b9989c
+oid sha256:0c372a6b95494631ec7edc64a6f3d5af8797bfe93b06ace8c9862a52228b0e3d
 size 147051

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ca7fb3f10b455bd7bd7287fd10ae52942e39151b881336e97cc5b706f80cb2
-size 208516
+oid sha256:917bb5f51939cf4ed05dd28f18fa216cf609760aeab3ecacf872ec5b4717817c
+size 202864

results.json

@@ -1 +1 @@
-{"mean_reward": 296.3126624274713, "std_reward": 13.369214323308904, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T06:28:01.930604"}
+{"mean_reward": 293.10131663899136, "std_reward": 16.591077563255766, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T08:09:28.072330"}