CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-Scale Pattern Generation

Jacob Schrum, Vanessa Volz, Sebastian Risi

    Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

    Abstract

    Generative Adversarial Networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no obvious way of combining multiple GAN outputs into a cohesive whole, which would be useful in many areas, such as the generation of video game levels. Game levels often consist of several segments, sometimes repeated directly or with variation, organized into an engaging pattern. Such patterns can be produced with Compositional Pattern Producing Networks (CPPNs). Specifically, a CPPN can define latent vector GAN inputs as a function of geometry, which provides a way to organize level segments output by a GAN into a complete level. This new CPPN2GAN approach is validated in both Super Mario Bros. and The Legend of Zelda. Specifically, divergent search via MAP-Elites demonstrates that CPPN2GAN can better cover the space of possible levels. The layouts of the resulting levels are also more cohesive and aesthetically consistent.
    Original languageEnglish
    Title of host publicationProceedings of the 2020 Genetic and Evolutionary Computation Conference
    Place of PublicationNew York, NY, USA
    PublisherAssociation for Computing Machinery
    Publication date2020
    Pages139–147
    ISBN (Print)9781450371285
    DOIs
    Publication statusPublished - 2020
    SeriesGECCO '20

    Keywords

    • indirect encoding
    • generative adversarial networks
    • neuroevolution
    • compositional pattern producing networks

    Fingerprint

    Dive into the research topics of 'CPPN2GAN: Combining Compositional Pattern Producing Networks and GANs for Large-Scale Pattern Generation'. Together they form a unique fingerprint.

    Cite this