Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 20.30 +/- 10.98
+      value: 46.80 +/- 15.41
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd6c9b5444bc842621cf05124982aa1d1a474c749c3196a23144680960430f53
+oid sha256:d631ec648edabd02a2957b9079321b0458b4f26016ef5f7e30cccb478c3d2ea6
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e36e5518d6740cb38e1eb383deaed8d979227f1cf13867d6d03ddf3ff1c1292d
-size 4253
+oid sha256:61de06718535a1557cca941aa7d9dedc37c3d92335e05ce0d40479721fa44b22
+size 8837

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 20.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T00:01:46.418231"}
+{"env_id": "CartPole-v1", "mean_reward": 46.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T00:36:42.338229"}