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: 7.50 +/- 2.63
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139f3b9a538ca047e137e7672a8d1e9b094b4447ae9ac0adc51764eb12739fdf
-size 1110
+oid sha256:af05a9d17d57478c8549ffc9864518cc442dc7a37b59e4fa1a92ffb27c921409
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:71d61065e395cd9867ddc23038eaf0e3e0cbcf5eda54c74bb65ba0362de79e0d
+size 120232

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-12-04T02:04:55.859329"}
+{"env_id": "Taxi-v3", "mean_reward": 7.5, "n_eval_episodes": 100, "eval_datetime": "2022-12-04T02:09:48.615274"}