Generating diverse opponents with multiobjective evolution

Alexandros Agapitos, Julian Togelius, Simon M. Lucas, Jürgen Schmidhuber, Andreas Konstantinidis

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers.

    Original languageEnglish (US)
    Title of host publication2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
    Pages135-142
    Number of pages8
    DOIs
    StatePublished - 2008
    Event2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 - Perth, WA, Australia
    Duration: Dec 15 2008Dec 18 2008

    Publication series

    Name2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008

    Other

    Other2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
    Country/TerritoryAustralia
    CityPerth, WA
    Period12/15/0812/18/08

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction

    Fingerprint

    Dive into the research topics of 'Generating diverse opponents with multiobjective evolution'. Together they form a unique fingerprint.

    Cite this