Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 9.60 +/- 9.60
+      value: 9.60 +/- 8.33
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d931063b43a22d9e48d1a5b15f0439c55915ceb2450dc7067f1b2a33af05ea5
-size 4831
+oid sha256:753936c8f223f892b44f05067ac164375c238d78d8e6259501aa14a6b8a7b6b2
+size 4639

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9e261a1aade087d45f4945bca25613c8a2c4d2f36429049fc0d70806416145
-size 15381
+oid sha256:cfe090a3afe03fee0d18ee19efcb343947b46886cfe1031f32f8b368244ce46d
+size 11736

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-17T17:01:23.091489"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-17T18:16:37.940170"}