---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
- huggingface-deep-rl-course
model-index:
- name: q-Taxi-v3
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: Taxi-v3
      type: Taxi-v3
    metrics:
    - type: mean_reward
      value: 7.48 +/- 2.78
      name: mean_reward
      verified: false
---
# Q-Learning Agent for Taxi-v3

Student: Sami Chellia
Hugging Face username: Sami94

This repository contains a Q-Learning agent trained for the Hugging Face Deep RL course.

Mean reward: 7.48 +/- 2.78

```python
from huggingface_hub import hf_hub_download
import pickle

model_path = hf_hub_download(repo_id="Sami94/q-Taxi-v3", filename="q-learning.pkl")
with open(model_path, "rb") as f:
    model = pickle.load(f)
```