first commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 293.10 +/- 16.59
+      value: 285.66 +/- 15.86
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c372a6b95494631ec7edc64a6f3d5af8797bfe93b06ace8c9862a52228b0e3d
+oid sha256:18e1851a4b387306c42e46c7ff881b1aa1f512f3ffaa6320ed0905a304c48225
 size 147051

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917bb5f51939cf4ed05dd28f18fa216cf609760aeab3ecacf872ec5b4717817c
-size 202864
+oid sha256:feda9bdc12de798ed260b35438c9111931d659957ebbfecf12aff2ee2184274d
+size 197114

results.json

@@ -1 +1 @@
-{"mean_reward": 293.10131663899136, "std_reward": 16.591077563255766, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T08:09:28.072330"}
+{"mean_reward": 285.6592076837315, "std_reward": 15.863112597284024, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-12T08:10:36.021673"}