Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: -2.60 +/- 1.56
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e653bd88645f6b47d37c1977f3b33c346f6dc63553cb73a2d171520831fffcc1
-size 4931
+oid sha256:ed202a60d442cce8bfbb9d130e5063090612037f46da4349b697699a01f45e7a
+size 5443

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a019cbd2a9fc7e301ac99b567dc3ac98f9bdbface2b15eaa26c68fb9e4457a2e
-size 2483
+oid sha256:46ac501dabd142ed069d55cdb459f39c5ef75c3483d8798e0a37872cc733d5b1
+size 4760

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-24T17:54:52.183044"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-24T22:27:28.130456"}