Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-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: FrozenLake-v1-no_slippery
-      type: FrozenLake-v1-no_slippery
+      name: Taxi-v3
+      type: Taxi-v3
 ---
 
   # **Q-Learning** Agent playing **FrozenLake-v1**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389185d03c693491e799d71f09d1c9f1296bc2f070cdf6c3163456d9bef62639
-size 904
+oid sha256:ce3cb01f56bf025e6485e2232f4ed6c705933419c10b386398e5e9fb4606c205
+size 24589

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
-size 28656
+oid sha256:5562e1ea314f2415ef59282c7a3732675348c355d78aedf5c348450480aa15f3
+size 113338

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-05-19T21:06:55.830674"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2022-05-19T21:12:11.362617"}