Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 46.80 +/- 15.41
+      value: 124.60 +/- 50.30
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d631ec648edabd02a2957b9079321b0458b4f26016ef5f7e30cccb478c3d2ea6
+oid sha256:ba8ae9df9c4f2efdaf266b2fb3649b02e8d5a2ea17de3e6b80f1e147fa40a66f
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61de06718535a1557cca941aa7d9dedc37c3d92335e05ce0d40479721fa44b22
-size 8837
+oid sha256:48627a530294118c46d764fbbd310c0b1df88c8886a9835d91ad96027e4cfeb4
+size 21549

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 46.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T00:36:42.338229"}
+{"env_id": "CartPole-v1", "mean_reward": 124.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T06:51:46.354831"}