Mutation Models: Learning to Generate Levels by Imitating Evolution

Ahmed Khalifa, Julian Togelius, Michael Cerny Green

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

    Abstract

    Search-based procedural content generation (PCG) is a well-known method for level generation in games. Its key advantage is that it is generic and able to satisfy functional constraints. However, due to the heavy computational costs to run these algorithms online, search-based PCG is rarely utilized for real-time generation. In this paper, we introduce mutation models, a new type of iterative level generator based on machine learning. We train a model to imitate the evolutionary process and use the trained model to generate levels. This trained model is able to modify noisy levels sequentially to create better levels without the need for a fitness function during inference. We evaluate our trained models on a 2D maze generation task. We compare several different versions of the method: training the models either at the end of evolution (normal evolution) or every 100 generations (assisted evolution) and using the model as a mutation function during evolution. Using the assisted evolution process, the final trained models are able to generate mazes with a success rate of and high diversity of . The trained model is many times faster than the evolutionary process it was trained on. This work opens the door to a new way of learning level generators guided by an evolutionary process, meaning automatic creation of generators with specifiable constraints and objectives that are fast enough for runtime deployment in games.

    Original languageEnglish (US)
    Title of host publicationProceedings of the 17th International Conference on the Foundations of Digital Games, FDG 2022
    EditorsKostas Karpouzis, Stefano Gualeni, Allan Fowler
    PublisherAssociation for Computing Machinery
    ISBN (Electronic)9781450397957
    DOIs
    StatePublished - Sep 5 2022
    Event17th International Conference on the Foundations of Digital Games, FDG 2022 - Athens, Greece
    Duration: Sep 5 2022Sep 8 2022

    Publication series

    NameACM International Conference Proceeding Series

    Conference

    Conference17th International Conference on the Foundations of Digital Games, FDG 2022
    Country/TerritoryGreece
    CityAthens
    Period9/5/229/8/22

    Keywords

    • Data Augmentation
    • Evolution
    • Expressive Range Analysis
    • Level Generation
    • Neural Networks
    • Procedural Content Generation
    • Surrogate Models

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Computer Networks and Communications
    • Computer Vision and Pattern Recognition
    • Software

    Fingerprint

    Dive into the research topics of 'Mutation Models: Learning to Generate Levels by Imitating Evolution'. Together they form a unique fingerprint.

    Cite this