On the Design of Game-Playing Agents

ISBN-13: 9783031009914 / Angielski / Miękka / 2017 / 188 str.

Eun-Youn Kim;Daniel Ashlock

Opis

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.

Spis treści

Preface.- Acknowledgments.- Introduction.- The First Place Where Trouble Arose.- Problems Beyond Representation.- Does All This Happen Outside of Prisoner's Dilemma?.- Noise!.- Describing and Designing Representations.- Bibliography.- Authors' Biographies .

O autorze

Dr. Eun-Youn Kim is a mathematician with a background in graph theory and evolutionary game theory, having worked extensively on the issue of representation in the design of gameplaying agents. Dr. Kim received her Ph.D. in mathematics from Iowa State University. She has been employed at the National Institute of Mathematical Sciences and the Korea Institute of Bioscience and Biotechnology in Korea. Dr. Kims research interests include broad interests in evolutionary computation applied to game playing and network modeling in biological systems. She is a member of the IEEE Computational Intelligence Societies technical committee on games and has helped organize international games conferences. Dr. Kim is currently employed by the department of basic science in Hanbat National University in South Korea.Dr. Daniel Ashlock is a professor of mathematics at the University of Guelph in Ontario, Canada. Dr. Ashlock received his Ph.D. in mathematics from Caltech with a focus in algebraic combinatorics. He was employed at Iowa State University before moving to Canada. Dr. Ashlock works on representation issues in evolutionary computation including games, optimization, bioinformatics, and theoretical biology. He holds the Bioinformatics Chair in the Department of Mathematics and Statistics at Guelph and serves on the editorial board of the IEEE Transactions on Evolutionary Computation, the IEEE Transactions on Games, The IEEE/ACM Transactions on Bioinformatics and Computational Biology, Biosystems, and Game and Puzzle Design. Dr. Ashlock serves on the IEEE Computational Intelligence Societies technical committees on games and bioinformatics and biomedical engineering.