Q-Learning on Taxi-v3 🚕

This project implements a Q-Learning agent trained on the Taxi-v3 environment as part of the Hugging Face Deep Reinforcement Learning Course (Unit 2).

---

🎥 Agent in Action

---

📌 Environment

• Taxi-v3
• 500 states
• 6 actions

---

⚙️ Algorithm

Tabular Q-Learning with epsilon-greedy exploration.

---

📊 Result

Mean reward > 4 (assignment requirement satisfied).

---

🤗 Hugging Face Model

https://huggingface.co/BhushanGatty/q-Taxi-v3

---

👨‍💻 Author

Bhushan Gatty
Robotics Engineering Student
Deep Reinforcement Learning Enthusiast