Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- FrozenLake-v1
+- Taxi-v3
 - q-learning
 - reinforcement-learning
 - custom-implementation
@@ -11,11 +11,11 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: FrozenLake-v1
-      type: FrozenLake-v1
+      name: Taxi-v3
+      type: Taxi-v3
     metrics:
     - type: mean_reward
-      value: 7.59 +/- 2.53
+      value: 7.40 +/- 2.82
       name: mean_reward
       verified: false
 ---

q-learning.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66334cb3198a17a9eb28532213e2b8d3363916b6c2ac905da6537ac77f66cbd2
-size 24374
+oid sha256:e90cee6c5f2a84e2a9e9098de5a3bc873a53fe6341e790bc1cdc6cd0daa8a37b
+size 24570

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0463ca0e1d1465137edeecfc88f7df5da48b5b308d98abcc29ed75124fd6353b
-size 106409
+oid sha256:a5fa90a361c587dc1a725e026ca264d744d3ca6609eb121d1688f387aba7982c
+size 130429

results.json

@@ -1 +1 @@
-{"env_id": "FrozenLake-v1", "mean_reward": 7.59, "n_eval_episodes": 100, "eval_datetime": "2026-04-01T14:04:24.231351"}
+{"env_id": "Taxi-v3", "mean_reward": 7.4, "n_eval_episodes": 100, "eval_datetime": "2026-04-01T14:06:03.734470"}