Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 193.50 +/- 45.78
+      value: 203.50 +/- 57.30
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4873c6f52f0fd40fb673a2357545e20aa02bb2dea7ee0f81199d920460cc1d88
-size 40129
+oid sha256:f8e294257fb6e6dc6c68fc736c34dbed8647734a4d7c772f5b3fd3887905f04a
+size 42241

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a609932d9bc5bb16469873ca4519e0fe3af1f236e2d43d0db491fe3694073ef
-size 22913
+oid sha256:723bd9bef3d91cbf57a2079b2ae5bb18af88963f0d0a89ff25bd0bf75a342741
+size 7744

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 193.5, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T17:48:23.324618"}
+{"env_id": "CartPole-v1", "mean_reward": 203.5, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T17:58:21.560391"}