Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 13.10 +/- 18.92
+      value: 10.60 +/- 9.50
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839db1867d703b9e475625a5fc41d9023a50bb82b2de4e898f99ae88cb819110
-size 9494
+oid sha256:333c3b6ce7f5a4ac4ef6aa876333d076f5ed41414b1658d679b573a682d6acf5
+size 13954

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-03T09:29:11.676822"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 10.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-03T09:30:12.609339"}