MACHINE LEARNING (often abbreviated ML, though in this book I will simply call it ‘learning’) is a hot topic in technology and business, and that excitement has filtered into games. In principle, learning AI has the potential to adapt to each player, learning their tricks and techniques and providing a consistent challenge. It has the potential to produce more believable characters: characters that can learn about their environment and use it to the best effect. It also has the potential to reduce the effort needed to create game-specific AI: characters should be able to learn about their surroundings and the tactical options that they provide.

In practice, it hasn’t yet fulfilled its promise, and not for want of trying. Applying learning ...

Get AI for Games, Third Edition, 3rd Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.