Evolving controllers for simulated car racing using object oriented genetic programming

Alexandros Agapitos, Julian Togelius, Simon Mark Lucas

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

    Abstract

    Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed.

    Original languageEnglish (US)
    Title of host publicationProceedings of GECCO 2007
    Subtitle of host publicationGenetic and Evolutionary Computation Conference
    Pages1543-1550
    Number of pages8
    DOIs
    StatePublished - 2007
    Event9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007 - London, United Kingdom
    Duration: Jul 7 2007Jul 11 2007

    Publication series

    NameProceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

    Other

    Other9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007
    CountryUnited Kingdom
    CityLondon
    Period7/7/077/11/07

    Keywords

    • Evolutionary computer games
    • Evolutionary robotics
    • Genetic programming
    • Homologous uniform crossover
    • Neural networks
    • Object-oriented
    • Subtree macro-mutation

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Theoretical Computer Science

    Fingerprint Dive into the research topics of 'Evolving controllers for simulated car racing using object oriented genetic programming'. Together they form a unique fingerprint.

    Cite this