Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.00 +/- 0.00
+      value: 0.83 +/- 0.37
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f65f02765e66a1fae2e7312dac49a8881ba1ea48a5d01a6a46d3f1d83f6fe9b
-size 24422
+oid sha256:310eea50d47a05e9a73c1843c073d788461979b5f99f5695813e9f9a6cc36642
+size 921

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0793296645743c2b34ee1a8b7c36c993950473056030769921b50a1f5df8fb5f
-size 38128
+oid sha256:ae242b8c5880a0f12136264b57caadb60080e1b73a43f1a7e507840f518cb3de
+size 35234

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T12:31:32.500249"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.8333333333333334, "n_eval_episodes": 100, "eval_datetime": "2022-05-21T12:32:53.829877"}