Artificial Intelligence and Games
Description
This book covers artificial intelligence methods applied to games, both in research and game development. It is aimed at graduate students, researchers, game developers, and readers with a technical background interested in the intersection of AI and games. The book covers a range of AI methods, from traditional search, planning, and optimization, to modern machine learning methods, including diffusion models and large language models. It discusses applications to playing games, generating content, and modeling players, including use cases such as level generation, game testing, intelligent non-player characters, player retention, player experience analysis, and game adaptation. It also covers the use of games, including video games, to test and benchmark AI algorithms. The book is informed by decades of research and practice in the field and combines insights into game design with deep technical knowledge from the authors, who have pioneered many of the methods and approaches used in the field.
This second edition of the 2018 textbook captures significant developments in AI and gaming over the past 7 years, incorporating advancements in computer vision, reinforcement learning, deep learning, and the emergence of transformer-based large language models and generative AI. The book has been reorganized to provide an updated overview of AI in games, with separate sections dedicated to AI's core uses in playing and generating games, and modeling their players, along with a new chapter on ethical considerations. Aimed at readers with foundational AI knowledge, the book primarily targets three audiences: graduate or advanced undergraduate students pursuing careers in game AI, AI researchers and educators seeking teaching resources, and game programmers interested in creative AI applications. The text is complemented by a website featuring exercises, lecture slides, and additional educational materials suitable for undergraduate and graduate courses.
Reviews / Votes
The original edition has been a vital reference for game developers. I'm glad to say that the new edition is still the indispensable overview of the field. And now it is up to date with the latest developments! If you make games, you need this book.
Raph Koster, CEO of Playable Worlds, author of A Theory of Fun
Games and virtual environments are important testbeds for artificial intelligence, and the authors are leading experts in applying AI to games.
Yann LeCun, Professor of Computer Science, New York University; Chief AI Scientist, Meta; ACM Turing Award
This book is a treasure trove of past achievements in game AI, and contains clues for future game AI development.
Youichiro Miyake, Lead AI Researcher, SQUARE ENIX
This book is an essential resource for anyone looking to expand their understanding of AI and its use in games. This revised edition refreshes and expands on the original and adds a much needed section on AI ethics. Highly recommended.
Stephen Peacock, Head of AI, Keywords Studios
More details
Other editions
Additional editions
Persons
Georgios N. Yannakakis is an Associate Professor at the Institute of Digital Games, University of Malta (UoM). He received his Ph.D. in informatics from the University of Edinburgh in 2006. He was previously an Associate Professor at the Center for Computer Games Research at the IT University of Copenhagen. His research lies at the crossroads of artificial intelligence, computational creativity, affective computing, and human-computer interaction with an emphasis on the domain of games. He has published over 200 journal and conference papers in the aforementioned fields, his research has been supported by numerous national and European grants, and it has been featured in Science Magazine and New Scientist among other publications. He is an associate editor of the IEEE Trans. on Computational Intelligence and AI in Games and was an associate editor of the IEEE Trans. on Affective Computing (2009-2016). He was the general chair of related key conferences such as IEEE CIG(Computational Intelligence and Games) and Foundations of Digital Games (FDG).
Julian Togelius is an Associate Professor in the Dept. of Computer Science and Engineering of New York University, and a codirector of the NYU Game Innovation Lab. He was previously an Associate Professor at the Center for Computer Games Research, IT University of Copenhagen. He works on all aspects of computational intelligence and games and on selected topics in evolutionary computation and evolutionary reinforcement learning. His current main research directions involve search-based procedural content generation, game adaptation through player modelling, automatic game design, and fair and relevant benchmarking of game AI through competitions. He is the Editor-in-Chief of the IEEE Transactions on Games.
Content
Foreword to the Second Edition.- Foreword to the First Edition.- Preface.- Acknowledgments.- Contents.- Acronyms.- Website.- 1. Introduction.- Part I. Background.- 2. AI Fundamentals.- 3. AI Methods for Games.- Part II. Play.- 4. Playing Games.- 5. Methods for Playing Games.- 6. Gameplaying AI by Game Genre.- Part III. Generate.-7. Procedural Content Generation.- 8. Methods for Generating Content.- 9. Procedural Content Generation by Content Type.- Part IV. Model.- 10. Player Modeling.- 11. From Observations to Models of Players.- 12. Player Modeling Exemplified.- Part V. The Road Ahead.- 13. Panorama and Map of Synergies.- 14. Frontiers of AI and Games Research.- 15. Ethics of AI and Games.- References.- Index.
