Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- Taxi-v3-4x4-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -9,14 +9,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4-no_slippery
-      type: FrozenLake-v1-4x4-no_slippery
+      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 sha256:7090b83c375f0ae8f12991c42ee2c1f5868ac73cf49bc9f1c435b8604087a6b9
-size 933
+oid sha256:492882431b66140cdae6bab19d949aa74a70309b3645106f495d84236e156084
+size 24618

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
-size 28656
+oid sha256:f984033a61afc66d332c5fd97b03885ce5d3d96791c8a6f09f2425c82f60045b
+size 36456

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-06T14:39:41.419622"}
+{"env_id": "Taxi-v3", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-06T14:40:16.011386"}