Computational Models of Motivation for Game-Playing Agents

• Main Author: Merrick, Kathryn E. (Author)
• Corporate Author: SpringerLink (Online service)
• Format: Electronic eBook
• Language: English
• Published: Cham : Springer International Publishing : Imprint: Springer, 2016.
• Subjects: Computer science.; Data mining.; Artificial intelligence.; Computational intelligence.; Computer Science.; Artificial Intelligence (incl. Robotics).; Computational Intelligence.; Data Mining and Knowledge Discovery.

 The focus of this book is on three influential cognitive motives: achievement, affiliation, and power motivation. Incentive-based theories of achievement, affiliation and power motivation are the basis for competence-seeking behaviour, relationship-building, leadership, and resource-controlling behaviour in humans. In this book we show how these motives can be modelled and embedded in artificial agents to achieve behavioural diversity. Theoretical issues are addressed for representing and embedding computational models of motivation in rule-based agents, learning agents, crowds and evolution of motivated agents. Practical issues are addressed for defining games, mini-games or in-game scenarios for virtual worlds in which computer-controlled, motivated agents can participate alongside human players. The book is structured into four parts: game playing in virtual worlds by humans and agents; comparing human and artificial motives; game scenarios for motivated agents; and evolution and the future of motivated game-playing agents. It will provide game programmers, and those with an interest in artificial intelligence, with the knowledge required to develop diverse, believable game-playing agents for virtual worlds. 

 From Player Types to Motivation -- Computational Models of Achievement, Affiliation, and Power Motivation -- Game Playing Agents and Non-player Characters -- Achievement Motivation -- Profiles of Achievement, Affiliation, and Power Motivation -- Enemies -- Pets and Partner Characters -- Support Characters -- Evolution of Motivated Agents -- Conclusion and Future Work. .