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 sha256:5f3f7e0baa276b5a8716a6e41bd4268c24ce213a3098dc932ea0d2508bef002f
-size 1131
+oid sha256:1b33088fc52423bd8ce3fa89ed90d95dd50bfdca686dd996f87a381d24b26256
+size 24591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
-size 28656
+oid sha256:50438ccf5df34de90e73302bd35874af3c272813cba12d2420998a3ffdf759d1
+size 109096

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-25T00:28:31.029426"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-25T00:49:46.454640"}