Evolving robust and specialized car racing skills

Julian Togelius, Simon M. Lucas

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

    Abstract

    Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able tn perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It Is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.

    Original languageEnglish (US)
    Title of host publication2006 IEEE Congress on Evolutionary Computation, CEC 2006
    Pages1187-1194
    Number of pages8
    StatePublished - 2006
    Event2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC, Canada
    Duration: Jul 16 2006Jul 21 2006

    Publication series

    Name2006 IEEE Congress on Evolutionary Computation, CEC 2006

    Other

    Other2006 IEEE Congress on Evolutionary Computation, CEC 2006
    Country/TerritoryCanada
    CityVancouver, BC
    Period7/16/067/21/06

    Keywords

    • Driving
    • Ear racing
    • Evolutionary robotics
    • Games
    • Incremental evolution

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Theoretical Computer Science

    Fingerprint

    Dive into the research topics of 'Evolving robust and specialized car racing skills'. Together they form a unique fingerprint.

    Cite this