Multi-population competitive co-evolution of car racing controllers

Julian Togelius, Peter Burrow, Simon M. Lucas

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

    Abstract

    Multi-population competitive co-evolution is explored as a way of developing controllers for a simple (but definitely not trivial) car racing game. The three main uses we see for this method are to evolve more complex general intelligence than would be possible with other methods, to compare different evolvable architectures for controllers, and to develop behaviourally diverse populations of agents for computer games. Nine-population co-evolution is compared with single-population co-evolution and standard evolution strategies, steady-state and generational versions of the algorithm are compared, and a number of different controller architectures are compared with each other.

    Original languageEnglish (US)
    Title of host publication2007 IEEE Congress on Evolutionary Computation, CEC 2007
    Pages4043-4050
    Number of pages8
    DOIs
    StatePublished - 2007
    Event2007 IEEE Congress on Evolutionary Computation, CEC 2007 - , Singapore
    Duration: Sep 25 2007Sep 28 2007

    Publication series

    Name2007 IEEE Congress on Evolutionary Computation, CEC 2007

    Other

    Other2007 IEEE Congress on Evolutionary Computation, CEC 2007
    Country/TerritorySingapore
    Period9/25/079/28/07

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Theoretical Computer Science

    Fingerprint

    Dive into the research topics of 'Multi-population competitive co-evolution of car racing controllers'. Together they form a unique fingerprint.

    Cite this