Push Q-Learning agent to Hub

README.md

@@ -9,7 +9,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.52 +/- 2.67
+      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:d131cab199805910e661082ffee0f98c84f87e4fc01fe57852bc48a06a57e697
+oid sha256:49bd3f98c281d734e5336288eff4589c35609056e49a3a14950e056d0f0eda59
 size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cef5441d9adb40b104d9516016b69b06b840a3aa7c4292f4ec72425a294516
-size 112532
+oid sha256:7a6ecdfe734abd6afa20082608d989125016e80bf1765928aaa990423cab4b66
+size 106886

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.52, "n_eval_episodes": 100, "eval_datetime": "2022-06-24T17:22:33.080572"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-24T17:32:39.488627"}