Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 5.70 +/- 8.46
+      value: 17.20 +/- 18.85
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538fb2fa994b090d4bfc57bcd11b79a37e475ea62b53f79a5314e6a8f5756eb4
+oid sha256:c7fd931c9b6fcbb9769d64d13ac589c3af5fe16fc50944a2bcb414e170d68d8e
 size 12319

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25518d7e40b25608ca4e73cdeaf1a6c4191de0c99a3eff789a126e17b97b1463
-size 3780
+oid sha256:f9e69173eff48f9a31095487acb67c3ee5b8b908a01847b9118ccc1136f5946b
+size 7656

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-05T18:04:27.010987"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 17.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-05T18:37:38.396823"}