Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+tags:
+- Taxi-v3
+- q-learning
+- reinforcement-learning
+- custom-implementation
+model-index:
+- name: Taxi-v3-trained
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Taxi-v3
+      type: Taxi-v3
+    metrics:
+    - type: mean_reward
+      value: 7.56 +/- 2.71
+      name: mean_reward
+      verified: false
+---
+
+ **Q-Learning** Agent playing **Taxi-v3**
+
+This is a trained **Q-Learning** agent for **Taxi-v3**.
+
+## Usage
+
+```python
+import json
+import numpy as np
+import gym
+
+qtable = np.load("qtable.npy")
+
+with open("config.json") as f:
+    config = json.load(f)
+
+env = gym.make(config["env_id"])
+model = {**config, "qtable": qtable}
+  ```
+  

config.json

@@ -0,0 +1,113 @@
+{
+  "env_id": "Taxi-v3",
+  "max_steps": 99,
+  "n_training_episodes": 25000,
+  "n_eval_episodes": 100,
+  "eval_seed": [
+    16,
+    54,
+    165,
+    177,
+    191,
+    191,
+    120,
+    80,
+    149,
+    178,
+    48,
+    38,
+    6,
+    125,
+    174,
+    73,
+    50,
+    172,
+    100,
+    148,
+    146,
+    6,
+    25,
+    40,
+    68,
+    148,
+    49,
+    167,
+    9,
+    97,
+    164,
+    176,
+    61,
+    7,
+    54,
+    55,
+    161,
+    131,
+    184,
+    51,
+    170,
+    12,
+    120,
+    113,
+    95,
+    126,
+    51,
+    98,
+    36,
+    135,
+    54,
+    82,
+    45,
+    95,
+    89,
+    59,
+    95,
+    124,
+    9,
+    113,
+    58,
+    85,
+    51,
+    134,
+    121,
+    169,
+    105,
+    21,
+    30,
+    11,
+    50,
+    65,
+    12,
+    43,
+    82,
+    145,
+    152,
+    97,
+    106,
+    55,
+    31,
+    85,
+    38,
+    112,
+    102,
+    168,
+    123,
+    97,
+    21,
+    83,
+    158,
+    26,
+    80,
+    63,
+    5,
+    81,
+    32,
+    11,
+    28,
+    148
+  ],
+  "learning_rate": 0.75,
+  "gamma": 0.95,
+  "max_epsilon": 1.0,
+  "min_epsilon": 0.05,
+  "decay_rate": 0.005
+}

qtable.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a422a58b26cb167cea958130f4bc8329b579ea56010a8759c30f956f7055114
+size 24128

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1480dde05748bb59481baf211c07811f1659649df71c1fd5bddf950cd168637a
+size 128598

results.json

@@ -0,0 +1 @@
+{"env_id": "Taxi-v3", "mean_reward": 7.56, "n_eval_episodes": 100, "eval_datetime": "2026-01-28T04:03:11.455336"}