Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 70.60 +/- 24.99
+      value: 20.30 +/- 10.98
       name: mean_reward
     task:
       type: reinforcement-learning

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1693c3289cc3f3afbb39619ca778cdcc2bd774abed8dd9fd474a454066ddba0
+oid sha256:dd6c9b5444bc842621cf05124982aa1d1a474c749c3196a23144680960430f53
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f6198e78f15ef533c9b87d7f4aa302f8c8989f4d025f45c5462a7bbb0303a6
-size 10432
+oid sha256:e36e5518d6740cb38e1eb383deaed8d979227f1cf13867d6d03ddf3ff1c1292d
+size 4253

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 70.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-10T15:31:40.756290"}
+{"env_id": "CartPole-v1", "mean_reward": 20.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-11T00:01:46.418231"}