Push Reinforce agent to the Hub

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: Reinforce-Pixelcopter-PLE-v0
   results:
-  - metrics:
-    - type: mean_reward
-      value: 11.60 +/- 8.81
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: Pixelcopter-PLE-v0
       type: Pixelcopter-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: 29.80 +/- 36.27
+      name: mean_reward
+      verified: false
 ---
 
   # **Reinforce** Agent playing **Pixelcopter-PLE-v0**

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:140af7c06b984edd93ecc7bf8dbc410169e1d0bc20f07f7e05669c3e21ee69c2
+oid sha256:0db280831a97ead8be306c86be78645c064f59305e6594f4dd7f8e2ca0cc0bd2
 size 4703

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20a93240fbb265cdce19ddc072225f4789a96be6fb7757dd540a162ab15b2e86
-size 8318
+oid sha256:6c541e9ef6a6a91eedb058b90365e244cd038e98c34feed372218c8451599738
+size 20463

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-20T09:47:33.087436"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 29.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-20T10:44:47.026711"}