Bootstrapping Conditional GANs for Video Game Level Generation

Ruben Rodriguez Torrado, Ahmed Khalifa, Michael Cerny Green, Niels Justesen, Sebastian Risi, Julian Togelius

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

    Abstract

    Generative Adversarial Networks (GANs) have shown impressive results for image generation. However, GANs face challenges in generating contents with certain types of constraints, such as game levels. Specifically, it is difficult to generate levels that have aesthetic appeal and are playable at the same time. Additionally, because training data usually is limited, it is challenging to generate unique levels with current GANs. In this paper, we propose a new GAN architecture named Conditional Embedding Self-Attention Generative Adversarial Net-work (CESAGAN) and a new bootstrapping training procedure. The CESAGAN is a modification of the self-attention GAN that incorporates an embedding feature vector input to condition the training of the discriminator and generator. This allows the network to model non-local dependency between game objects, and to count objects. Additionally, to reduce the number of levels necessary to train the GAN, we propose a bootstrapping mechanism in which playable generated levels are added to the training set. The results demonstrate that the new approach does not only generate a larger number of levels that are playable but also generates fewer duplicate levels compared to a standard GAN.

    Original languageEnglish (US)
    Title of host publicationIEEE Conference on Games, CoG 2020
    PublisherIEEE Computer Society
    Pages41-48
    Number of pages8
    ISBN (Electronic)9781728145334
    DOIs
    StatePublished - Aug 2020
    Event2020 IEEE Conference on Games, CoG 2020 - Virtual, Osaka, Japan
    Duration: Aug 24 2020Aug 27 2020

    Publication series

    NameIEEE Conference on Computatonal Intelligence and Games, CIG
    Volume2020-August
    ISSN (Print)2325-4270
    ISSN (Electronic)2325-4289

    Conference

    Conference2020 IEEE Conference on Games, CoG 2020
    CountryJapan
    CityVirtual, Osaka
    Period8/24/208/27/20

    Keywords

    • Bootstrapping
    • Conditional Embedding
    • Functional Content Generation
    • General Video Game Framework
    • Generative Adversarial Networks
    • Procedural Content Generation
    • Self-Attention

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction
    • Software

    Fingerprint Dive into the research topics of 'Bootstrapping Conditional GANs for Video Game Level Generation'. Together they form a unique fingerprint.

    Cite this