Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 124.60 +/- 50.30
+      value: 41.90 +/- 9.87
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba8ae9df9c4f2efdaf266b2fb3649b02e8d5a2ea17de3e6b80f1e147fa40a66f
+oid sha256:93596aed6aa564d16213b22ce691f1310c860395c2aa484818fdd096a6b9aae3
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48627a530294118c46d764fbbd310c0b1df88c8886a9835d91ad96027e4cfeb4
-size 21549
+oid sha256:2e213b6ce6997a924bab6a971f1cd7a7949110fc5dc40244c34ba1f825131e47
+size 6654

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 124.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T06:51:46.354831"}
+{"env_id": "CartPole-v1", "mean_reward": 41.9, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-12T14:34:51.109622"}