Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Taxi-v3
+- Taxi-v3-4x4-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 7.56 +/- 2.71
+      value: 0.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v3
-      type: Taxi-v3
+      name: Taxi-v3-4x4-no_slippery
+      type: Taxi-v3-4x4-no_slippery
 ---
 
   # **Q-Learning** Agent playing **Taxi-v3**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af3a40b925635a393d0e982598532436f6f405b30a050ba74270e8b46aaa4bfe
-size 24589
+oid sha256:0ea9ae02d6824305f0a52752f2f67f0cf447388ce89fcf11134114a1ce9be112
+size 24618

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32fc695ee71dc75017939e21ab9462f7d54685e11fa45db2808746a4502409c
-size 103002
+oid sha256:f984033a61afc66d332c5fd97b03885ce5d3d96791c8a6f09f2425c82f60045b
+size 36456

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-06-04T07:04:26.891461"}
+{"env_id": "Taxi-v3", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-06-04T08:40:42.541807"}