Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 5.50 +/- 4.92
+      value: 9.60 +/- 9.60
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e020e46b2372ce606ea2a9c386b35c2f2a16cbb444ee0cb97e926f9127d4d73
-size 7791
+oid sha256:3e9e261a1aade087d45f4945bca25613c8a2c4d2f36429049fc0d70806416145
+size 15381

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.5, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-17T16:59:50.135640"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-17T17:01:23.091489"}