Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Taxi-v3-4x4-no_slippery
+- Taxi-v3
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v3-4x4-no_slippery
-      type: Taxi-v3-4x4-no_slippery
+      name: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 7.56 +/- 2.71
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5a24b858bb0a1d77fa6f2de1fae5be9f59482a7c16130c73db5e8c8d6a3965
-size 24601
+oid sha256:5c616fe868624f7b4f9c3d3f9777ca44f65e4999c8a7924731b6c61d157137b6
+size 24572

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:52d78b3d3bf58593bb402a68ca217047acc04ba4161d36374ea369084a993634
+size 118871

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-12-19T00:01:02.003042"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-12-19T00:09:13.753548"}