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: 1.00 +/- 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:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
-size 24589
+oid sha256:7c485261c90c27e7b097fb879820f9ed84af66510a5f2acb1bfd8d45bf2fbd13
+size 24620

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cddeb2b6458350256bca0a4237d02090d182ce7da98bd1a872479a91ff6ad3e
-size 106225
+oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
+size 28656

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-25T20:17:28.148005"}
+{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-25T20:28:03.523380"}