Predicting resource locations in game maps using deep convolutional neural networks

Scott Lee, Aaron Isaksen, Christoffer Holmgard, Julian Togelius

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

    Abstract

    We describe an application of neural networks to predict the placements of resources in StarCraft II maps. Networks are trained on existing maps taken from databases of maps actively used in online competitions and tested on unseen maps with resources (minerals and vespene gas) removed. This method is potentially useful for Al-Assisted game design tools, allowing the suggestion of resource and base placements consonant with implicit StarCraft II design principles for fully or partially sketched heightmaps. By varying the thresholds for the placement of resources, more or fewer resources can be created consistently with the pattern of a single map. We further propose that these networks can be used to help understand the design principles of StarCraft II maps, and by extension other, similar types of game content.

    Original languageEnglish (US)
    Title of host publicationWS-16-21
    Subtitle of host publicationArtificial Intelligence in Adversarial Games; WS-16-22: Experimental AI in Games; WS-16-23: Player Analytics
    PublisherAI Access Foundation
    Pages46-52
    Number of pages7
    ISBN (Electronic)9781577357735
    StatePublished - 2016
    Event12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016 - Burlingame, United States
    Duration: Oct 8 2016Oct 9 2016

    Publication series

    NameAAAI Workshop - Technical Report
    VolumeWS-16-21 - WS-16-23

    Other

    Other12th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2016
    Country/TerritoryUnited States
    CityBurlingame
    Period10/8/1610/9/16

    ASJC Scopus subject areas

    • General Engineering

    Fingerprint

    Dive into the research topics of 'Predicting resource locations in game maps using deep convolutional neural networks'. Together they form a unique fingerprint.

    Cite this