Push Reinforce agent to the Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 5.30 +/- 1.90
+      value: 5.10 +/- 4.91
       name: mean_reward
       verified: false
 ---

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d88f1837ea7afbe0128adc7426f23d8cdd4ef0137047343bf654397ebddcfa95
-size 4703
+oid sha256:73d706c0555716113afbc7496ad05094c16966c1a812e7eab5833665dd581147
+size 38999

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4987cb3125fb7777ff9ca2cd26f320ffe8c0f5e4f2aa80e2eb8e87071734ac18
-size 16275
+oid sha256:019450b3b1517a672603f8dd10c91f9942afcc1b436b4ce7c6f18f448313f6b9
+size 6949

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-15T09:47:07.601921"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-15T15:10:39.068536"}