Synthesis Lectures on Games and Computational Intelligence – serie

This book is a formalization of collected notes from an introductory game theory course taught at Queen's University. The course introduced traditional game theory and its formal analysis, but also moved to more modern approaches to game theory, providing a broad introduction to the current state of the discipline. Classical games, like the Prisoner's Dilemma and the Lady and the Tiger, are joined by a procedure for transforming mathematical games into card games. Included is an introduction and brief investigation into mathematical games, including combinatorial games such as Nim. The text examines techniques for creating tournaments, of the sort used in sports, and demonstrates how to obtain tournaments that are as fair as possible with regards to playing on courts. The tournaments are tested as in-class learning events, providing a novel curriculum item. Example tournaments are provided at the end of the book for instructors interested in running a tournament in their own classroom.The book is appropriate as a text or companion text for a one-semester course introducing the theory of games or for students who wish to get a sense of the scope and techniques of the field.

Evolving agents to play games is a promising technology. It can provide entertaining opponents for games like Chess or Checkers, matched to a human opponent as an alternative to the perfect and unbeatable opponents embodied by current artifical intelligences. Evolved agents also permit us to explore the strategy space of mathematical games like Prisoner's Dilemma and Rock-Paper-Scissors. This book summarizes, explores, and extends recent work showing that there are many unsuspected factors that must be controlled in order to create a plausible or useful set of agents for modeling cooperation and conflict, deal making, or other social behaviors. The book also provides a proposal for an agent training protocol that is intended as a step toward being able to train humaniform agents—in other words, agents that plausibly model human behavior.

Automatic content generation is the production of content for games, web pages, or other purposes by procedural means. Search-based automatic content generation employs search-based algorithms to accomplish automatic content generation. This book presents a number of different techniques for search-based automatic content generation where the search algorithm is an evolutionary algorithm. The chapters treat puzzle design, the creation of small maps or mazes, the use of L-systems and a generalization of L-system to create terrain maps, the use of cellular automata to create maps, and, finally, the decomposition of the design problem for large, complex maps culminating in the creation of a map for a fantasy game module with designersupplied content and tactical features.The evolutionary algorithms used for the different types of content are generic and similar, with the exception of the novel sparse initialization technique are presented in Chapter 2. The points where the content generation systems vary are in the design of their fitness functions and in the way the space of objects being searched is represented. A large variety of different fitness functions are designed and explained, and similarly radically different representations are applied to the design of digital objects all of which are, essentially, maps for use in games.

Cooperation is pervasive throughout nature, but its origin remains an open question. For decades, social scientists, business leaders, and economists have struggled with an important question: why is cooperation so ubiquitous among unrelated humans? The answers would have profound effects because anything that promotes cooperation leads to more productive work environments and benefits society at large. Game theory provides an ideal framework for studying social dilemmas, or those situations in which people decide whether to cooperate with others (benefitting the group) or defect by prioritizing their self-interest (benefitting only the individual). The social dilemma is formulated as a mathematical game and then programmed into a computer model. Simulating the game allows researchers to investigate potential theories to explain how cooperation emerges and what promotes its persistence.Over the past 25 years, countless papers on social dilemma games have been published, yet arguably little progress has been made. The problem is the social dilemma game models are unrealistic in the sense they contain artificial constructs that deviate from the way humans act. This book describes the shortcomings in current social dilemma game modeling techniques and provides guidance on designing more effective models. A basic introduction to game theory is provided with an emphasis on the prisoner's dilemma, the most widely studied social dilemma game. Individual chapters are provided detailing the shortcomings of weak selection, spatial games, and the Moran process. Computer model validation is also discussed at length. The recommendations found in this book should help design more realistic social dilemma game models likely to produce a better understanding of human cooperation.

Research on general video game playing aims at designing agents or content generators that can perform well in multiple video games, possibly without knowing the game in advance and with little to no specific domain knowledge. The general video game AI framework and competition propose a challenge in which researchers can test their favorite AI methods with a potentially infinite number of games created using the Video Game Description Language. The open-source framework has been used since 2014 for running a challenge. Competitors around the globe submit their best approaches that aim to generalize well across games. Additionally, the framework has been used in AI modules by many higher-education institutions as assignments, or as proposed projects for final year (undergraduate and Master's) students and Ph.D. candidates. The present book, written by the developers and organizers of the framework, presents the most interesting highlights of the research performed by the authors duringthese years in this domain. It showcases work on methods to play the games, generators of content, and video game optimization. It also outlines potential further work in an area that offers multiple research directions for the future.

Games, whether educational or recreational, are meant to be fun. How do we ensure that the game delivers its intent?The answer to this question is playtesting. However, a haphazard playtest process cannot discover play experience from various dimensions. Players' perceptions, affordances, age, gender, culture, and many more human factors influence play experience. A playtest requires an intensive experimental process and scientific protocols to ensure that the outcomes seen are reliable for the designer.Playtesting and players' affordances are the focus of this book. This book is not just about the playtest procedures but also demonstrates how they lead to the conclusions obtained when considering data sets. The playtest process or playtest stories differ according to the hypothesis under investigation. We cover examples of playtesting to identify the impact of human factors, such as age and gender, to examine a player's preferences for game objects' design and colors. The book details topics to reflect on possible emotional outcomes of the player at the early stages of game design as well as the methodology for presenting questions to players in such a way as to elicit authentic feedback.This book is intended mainly for game designers, researchers, and developers. However, it provides a general understanding of affordances and human factors that can be informative for readers working in any domain.

This book surveys current and future approaches to generating video game content with machine learning or Procedural Content Generation via Machine Learning (PCGML).  Machine learning is having a major impact on many industries, including the video game industry.  PCGML addresses the use of computers to generate new types of content for video games (game levels, quests, characters, etc.) by learning from existing content.  The authors illustrate how PCGML is poised to transform the video games industry and provide the first ever beginner-focused guide to PCGML.  This book features an accessible introduction to machine learning topics, and readers will gain a broad understanding of currently employed PCGML approaches in academia and industry.  The authors provide guidance on how best to set up a PCGML project and identify open problems appropriate for a research project or thesis.  This book is written with machine learning and games novices in mind and includes discussions of practical and ethical considerations along with resources and guidance for starting a new PCGML project.

This second edition updates and expands upon the first beginner-focused guide to Procedural Content Generation via Machine Learning (PCGML), which is the use of computers to generate new types of content for video games (game levels, quests, characters, etc.) by learning from existing content. The authors survey current and future approaches to generating video game content and illustrate the major impact that PCGML has had on video games industry. In order to provide the most up-to-date information, this new edition incorporates the last two years of research and advancements in this rapidly developing area. The book guides readers on how best to set up a PCGML project and identify open problems appropriate for a research project or thesis. The authors discuss the practical and ethical considerations for PCGML projects and demonstrate how to avoid the common pitfalls. This second edition also introduces a new chapter on Generative AI, which covers the benefits, risks, and methods for applying pre-trained transformers to PCG problems.