Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Taxi-v3-4x4-no_slippery
+- Taxi-v3
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Taxi-v3-4x4-no_slippery
-      type: Taxi-v3-4x4-no_slippery
+      name: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 1.00 +/- 0.00
+      value: 7.56 +/- 2.71
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfc616fa278a9a51732a4b6086c1f79657079aa99d64d2576ef45ef01788255
-size 1113
+oid sha256:fe8348cb8be045f81b6641020dd0d89ebe0e775e8033e13f1973656d6d516fab
+size 24573

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68575109feae93277e5fddb0f18cc8f0eea5597011ee71d6525e5a431d469450
-size 31168
+oid sha256:c433bddd4761d22df0b74a28f7002fb8e9a8635ba7c4ae913218c297d4105c20
+size 119098

results.json

@@ -1 +1 @@
-{"env_id": "Taxi-v3", "mean_reward": 1.0, "n_eval_episodes": 100, "eval_datetime": "2025-12-26T07:36:58.821397"}
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2025-12-26T08:36:34.904063"}