Alphastar: An evolutionary computation perspective

Kai Arulkumaran, Antoine Cully, Julian Togelius

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

    Abstract

    In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI. AlphaStar draws on many areas of AI research, including deep learning, reinforcement learning, game theory, and evolutionary computation (EC). In this paper we analyze AlphaStar primarily through the lens of EC, presenting a new look at the system and relating it to many concepts in the field. We highlight some of its most interesting aspects-the use of Lamarckian evolution, competitive co-evolution, and quality diversity. In doing so, we hope to provide a bridge between the wider EC community and one of the most significant AI systems developed in recent times.

    Original languageEnglish (US)
    Title of host publicationGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion
    PublisherAssociation for Computing Machinery, Inc
    Pages314-315
    Number of pages2
    ISBN (Electronic)9781450367486
    DOIs
    StatePublished - Jul 13 2019
    Event2019 Genetic and Evolutionary Computation Conference, GECCO 2019 - Prague, Czech Republic
    Duration: Jul 13 2019Jul 17 2019

    Publication series

    NameGECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

    Conference

    Conference2019 Genetic and Evolutionary Computation Conference, GECCO 2019
    Country/TerritoryCzech Republic
    CityPrague
    Period7/13/197/17/19

    Keywords

    • Co-evolution
    • Lamarckian evolution
    • Quality diversity

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Theoretical Computer Science
    • Software

    Fingerprint

    Dive into the research topics of 'Alphastar: An evolutionary computation perspective'. Together they form a unique fingerprint.

    Cite this