Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 14.00 +/- 11.66
+      value: 18.70 +/- 15.13
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:739b9e5b7d0c1f88e00b6cf4acfc3f9010c7e0e2f879b9f781f57078d55a67cc
+oid sha256:287024b1b831c7c9b9bf4ddf63c0ca784780726250f4cfcc2f6c66154d8adf8b
 size 4703

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305389e3dfe1eabf8befa0dc4427852114f70a2d9d95fa10486ef659087772ea
-size 12815
+oid sha256:f79c103918222991f95dc637e92295768dc0f06f6af4ca216c3199d45ba37c4d
+size 10765

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T08:15:21.459215"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-12T16:03:15.807204"}