Neuroevolutionary Constrained Optimization for Content Creation

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


    This paper presents a constraint-based procedural
    content generation (PCG) framework used for the creation of
    novel and high-performing content. Specifically, we examine
    the efficiency of the framework for the creation of spaceship
    design (hull shape and spaceship attributes such as weapon and
    thruster types and topologies) independently of game physics
    and steering strategies. According to the proposed framework,
    the designer picks a set of requirements for the spaceship
    that a constrained optimizer attempts to satisfy. The constraint
    satisfaction approach followed is based on neuroevolution;
    Compositional Pattern-Producing Networks (CPPNs) which
    represent the spaceship’s design are trained via a constraint-based
    evolutionary algorithm. Results obtained in a number
    of evolutionary runs using a set of constraints and objectives
    show that the generated spaceships perform well in movement,
    combat and survival tasks and are also visually appealing.
    TitelComputational Intelligence and Games (CIG). IEEE Conference on
    ForlagIEEE Computer Society Press
    ISBN (Trykt)978-1-4577-0010-1
    ISBN (Elektronisk)978-1-4577-0009-5
    StatusUdgivet - 2011
    BegivenhedIEEE Conference on Computational Intelligence and Games 2011: A series of international meetings focused on the applications of computational intelligence to games - Seoul, Sydkorea
    Varighed: 31 aug. 20113 sep. 2011


    KonferenceIEEE Conference on Computational Intelligence and Games 2011


    Dyk ned i forskningsemnerne om 'Neuroevolutionary Constrained Optimization for Content Creation'. Sammen danner de et unikt fingeraftryk.