Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- FrozenLake-v1-8x8
 - 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: FrozenLake-v1-8x8
+      type: FrozenLake-v1-8x8
 ---
 
   # **Q-Learning** Agent playing **FrozenLake-v1**

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48fc6dd8b004fc6aaf12a387fc1fd04bd349441634e8816ee814791778cda490
-size 933
+oid sha256:97831b9c22b8ef5a056aa7202078d693ef9d2d7a8bba5b38bfbdc3978fae75fc
+size 2459

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24c9a80acba57779e3cdcb22355516cca039d869c3b90ebbf7b9c730a3dd91ea
-size 28656
+oid sha256:585fce0a26b8d3e1a9d4c406a5bc50a41dfbbd0cebff0ccbc405456a3a8ec90e
+size 159419

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2022-07-18T16:09:48.756601"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2022-08-17T09:02:02.114283"}