Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 17.20 +/- 15.35
+      value: 14.00 +/- 11.66
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd858c1f99d9a5d01fc9ab8df7e5f6dffd5dc056ea1d039fd8b9d568efd9ad3
+oid sha256:739b9e5b7d0c1f88e00b6cf4acfc3f9010c7e0e2f879b9f781f57078d55a67cc
 size 4703

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b50502ee1fdaad2c5f757c172c0a430ea1d5e9d7d39079c2c82217103c36efb
-size 20391
+oid sha256:305389e3dfe1eabf8befa0dc4427852114f70a2d9d95fa10486ef659087772ea
+size 12815

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 17.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T02:03:08.467830"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T08:15:21.459215"}