Please subscribe to our YouTube channel @ https://www.youtube.com/@DevoxxForever
Subscribe to LinkedIn @ https://www.linkedin.com/company/voxxed-days-amsterdam
Follow us on Twitter @ https://twitter.com/voxxedamsterdam

AI has become part of our everyday lives but we often forget one of its earliest and most fascinating uses: creating an opponent to play games with.

We’ve seen it in chess, Go, and countless video games, where AI opponents follow complex strategies or fixed rule sets. But who says you need PyTorch or TensorFlow to do it? Sometimes, the good old Java is all you need.

In this talk, I’ll share how I built a Deep Q-Network (DQN) in Java to teach an AI to play the board game Azul. I’ll cover environment design, state encoding, reward shaping, and training strategies.

Devoxx

A developer at CERN built a Deep Q-Network (DQN) AI in plain Java to play the board game Azul, implementing the neural network from scratch without third-party ML libraries. The talk covers the game's rules and state representation, Q-learning fundamentals, how a neural network replaces the Q-table, the dueling DQN architecture where two networks compete to accelerate learning, state encoding, epsilon-greedy exploration policy, and a live CLI demo showing the trained AI making reasonable moves.

Training My Rival in Java: A Deep Q-Learning AI to Play Azul by Victor Uria Valle