Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.28 +/- 2.90
+      value: 7.56 +/- 2.71
       name: mean_reward
     task:
       type: reinforcement-learning

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdb2412da7c9ce2ee813602fce6822b11356377635e92004699c8dba7575db5
-size 24589
+oid sha256:8c2764ad583b29868d6ecd910d8d991d6c8a02b26ee3d5203e1a401a556fad99
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca34ea4eea92d7b2b2142e4d49910e816ca4e4674ef0ffa1428b735d37117a0d
-size 108732
+oid sha256:d15a4256509b8b0d833086dedd4ee11d4e8bfe437d8f1d63b6af10858f3939e0
+size 96693

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.28, "n_eval_episodes": 100, "eval_datetime": "2022-06-18T14:41:41.554271"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-18T14:55:53.147778"}