Biography
Kathryn Merrick is an associate professor in information technology at the University of New South Wales, Canberra. Kathryn’s research interests lie in the field of autonomous mental development for machines, including machine learning. Kathryn’s research speciality within this domain is the development, use and evaluation of computational models of motivation. Kathryn has contributed to the theoretical development of computational motivation in reinforcement learning, particle swarm optimisation and game theoretic settings. Applications of Kathryn’s research include the control of believable digital characters in online games, intelligent sensed environments, and developmental robots. Her research has attracted $1.5 million in research funding from sources such as the Australian Research Council and the Defence Science and Technology Group. She has over 60 publications including two books.
Abstract
Achievement, affiliation, and power: computational motivation for game-playing agents
In recent years, two goals have been emerging to focus artificial intelligence research for games. The first is concerned with building more believable and exciting virtual worlds in which to play games. The second is concerned with developing our understanding of game players so that we can adapt games to optimise player experience. This talk will explain how computational models of motivation can be used to further research towards both of these goals. First, I will introduce three influential motivation theories for achievement, affiliation and power motivation. I will explain the psychology theory for each of these motivations then examine two approaches to modelling them computationally. The approach aims to permit these motivations to be embedded in computer controlled game-playing agents to create diverse non-player characters for computer games. The approach aims to allow us to identify when these motivations are displayed by humans during game-play. I will discuss our experiments, results and progress in each area.
