What has general game playing got to do with player modelling? Is procedural content generation relevant for research in believable agents? Can interactive narrative teach us about AI-assisted game design? This tutorial attempts to explain how everything fits together within our research field. We divide the whole field of CI/AI in Games into ten different research areas, and then we try to explain how they influence each other. Perhaps more importantly, we try to explain how these areas could influence each other, but don't yet. In other words, we will be suggesting what we consider interesting topics for future research, as well as trying to give a coherent picture of the whole field. We will endeavour to make the tutorial accessible to both newcomers to CIG research and seasoned veterans, to the extent there are any in this young field of ours.
Julian Togelius is Associate Professor at the Center for Computer Games Research, IT University of Copenhagen, Denmark. 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 in games, game adaptation through player modelling, automatic game design, and fair and relevant benchmarking of game AI through competitions. He is a past chair of the IEEE CIS Technical Committee on Games, and an associate editor of IEEE Transactions on Computational Intelligence and Games. Togelius holds a BA from Lund University, an MSc from the University of Sussex, and a PhD from the University of Essex.
Georgios N. Yannakakis (yannakakis.net) received the Ph.D. degree in informatics from the University of Edinburgh in 2005. Prior to joining the Institute of Digital Games, University of Malta, Msida, Malta in 2012, he was an Associate Professor at (and is still affiliated with) the Center for Computer Games Research, IT University of Copenhagen. He does research at the crossroads of AI, affective computing, advanced game technology, and human computer interaction. He has published over 150 journal and international conference papers in the aforementioned fields and his work has been supported by several EU and national research grants. He is an Associate Editor of the IEEE Transactions on Affective Computing and the IEEE Transactions on Computational Intelligence and AI in Games.
Many biological, social and economic processes are naturally modeled as a system of interacting individuals. Game theory provides a natural framework for capturing behavior in such systems. In particular, game theory techniques have been widely used to study one of the great open questions in nature: how does cooperation grow in populations? This talk provides an introduction to evolutionary game theory, which combines the principles of evolution and classical game theory to see how cooperative behavior might evolve in populations. The talk begins with a brief introduction to classical game theory covering concepts such as payoff matrices, Nash equilibrium, and evolutionary stable strategies. Widely investigated games such as the iterated prisoner’s dilemma and the hawk-dove game will also be discussed. From there the fundamentals of evolutionary game theory are presented. Concepts such as frequency dependent fitness selection, evolution in finite populations via the Moran process, spatial games, and public goods games will be discussed. A survey of the recent work in this area is presented along with a critique on what has been accomplished and where future research efforts should concentrate.
Garry Greenwood is Associate Professor at Portland State University. After spending more than a decade in industry designing multiprocessor embedded system hardware, he entered academia. His research interests are evolvable hardware, adaptive systems, and operator methods in quantum computing. Dr. Greenwood is a member of Tau Beta Pi, Eta Kappa Nu, and is a registered Professional Engineer. He was a National Science Foundation Scholar-in-Residence at the National Institutes of Health from 1999 and 2000. He is Editor in Chief of the IEEE Transactions on Evolutionary Computation.