Learning to Generate Levels from Nothing

Philip Bontrager, Julian Togelius

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


    Machine learning for procedural content generation has recently become an active area of research. Levels vary in both form and function and are mostly unrelated to each other across games. This has made it difficult to assemble suitably large datasets to bring machine learning to level design in the same way as it's been used for image generation. Here we propose Generative Playing Networks which design levels for itself to play. The algorithm is built in two parts; an agent that learns to play game levels, and a generator that learns the distribution of playable levels. As the agent learns and improves its ability, the space of playable levels, as defined by the agent, grows. The generator targets the agents playability estimates to then update its understanding of what constitutes a playable level. We call this process of learning the distribution of data found through self-discovery with an environment, self-supervised inductive learning. Unlike previous approaches to procedural content generation, Generative Playing Networks are end-to-end differentiable and does not require human-designed examples or domain knowledge. We demonstrate the capability of this framework by training an agent and level generator for a 2D dungeon crawler game.

    Original languageEnglish (US)
    Title of host publication2021 IEEE Conference on Games, CoG 2021
    PublisherIEEE Computer Society
    ISBN (Electronic)9781665438865
    StatePublished - 2021
    Event2021 IEEE Conference on Games, CoG 2021 - Copenhagen, Denmark
    Duration: Aug 17 2021Aug 20 2021

    Publication series

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


    Conference2021 IEEE Conference on Games, CoG 2021


    • General Video Game AI (GVGAI)
    • Generative
    • Procedural Content Generation (PCG)
    • Reinforcement Learning (RL)

    ASJC Scopus subject areas

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


    Dive into the research topics of 'Learning to Generate Levels from Nothing'. Together they form a unique fingerprint.

    Cite this