Push Q-Learning agent to Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1-4x4-no_slippery
+- FrozenLake-v1-8x8-no_slippery
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1-4x4-no_slippery
-      type: FrozenLake-v1-4x4-no_slippery
+      name: FrozenLake-v1-8x8-no_slippery
+      type: FrozenLake-v1-8x8-no_slippery
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 0.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57f82a27c3d4c8922873d85e3817ac52e066b53ea91288472c7cfd1a57ef3cd
-size 934
+oid sha256:31f0e08ece49207d2abfef9c35a258eba962d5c532cdd7c594098267e2ecfb81
+size 2470

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9aa294c2e71e126fa3ff08a8d8b9fa601940fc5e16a67fe30df8bfe8a867bfc
-size 31966
+oid sha256:f02603f37cc4e5c52c813d897d0791ccf9fc3a16eb379d3537331be570a2c7fa
+size 134994

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2025-04-11T08:14:48.295745"}
+{"env_id": "FrozenLake-v1", "mean_reward": 0.0, "n_eval_episodes": 100, "eval_datetime": "2025-04-11T08:17:12.410800"}