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
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 7.56 +/- 2.71
       name: mean_reward
     task:
       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
 ---
 
   # **Q-Learning** Agent playing **Taxi-v3**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ca2fea50cc76010c4541fa7720369e3fa5e6d78233333056262527a4e87886
-size 1129
+oid sha256:55a514c0e2125f83a0fb64fcb71dd461f171a7f9d196d196064928731cc588e1
+size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ba66361f81e2d1dc4305e8bf921c20f263b0bc4d100906461f7c0c85364958
-size 31943
+oid sha256:244235efa7dd7bac549e2296a273af292fc7b20f40bf7642cff45be1bf657380
+size 120742

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-25T18:23:16.560808"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-07-25T18:25:38.904695"}