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
    CountryCzech Republic
    CityPrague
    Period7/13/197/17/19

    Fingerprint

    Evolutionary Computation
    Evolutionary algorithms
    Artificial intelligence
    Artificial Intelligence
    Coevolution
    Game theory
    Reinforcement learning
    Beat
    Game Theory
    Reinforcement Learning
    Lens
    Lenses
    Game

    Keywords

    • Co-evolution
    • Lamarckian evolution
    • Quality diversity

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Theoretical Computer Science
    • Software

    Cite this

    Arulkumaran, K., Cully, A., & Togelius, J. (2019). Alphastar: An evolutionary computation perspective. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion (pp. 314-315). (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). Association for Computing Machinery, Inc. https://doi.org/10.1145/3319619.3321894

    Alphastar : An evolutionary computation perspective. / Arulkumaran, Kai; Cully, Antoine; Togelius, Julian.

    GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. p. 314-315 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).

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

    Arulkumaran, K, Cully, A & Togelius, J 2019, Alphastar: An evolutionary computation perspective. in GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion, Association for Computing Machinery, Inc, pp. 314-315, 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, Prague, Czech Republic, 7/13/19. https://doi.org/10.1145/3319619.3321894
    Arulkumaran K, Cully A, Togelius J. Alphastar: An evolutionary computation perspective. In GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc. 2019. p. 314-315. (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion). https://doi.org/10.1145/3319619.3321894
    Arulkumaran, Kai ; Cully, Antoine ; Togelius, Julian. / Alphastar : An evolutionary computation perspective. GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, Inc, 2019. pp. 314-315 (GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion).
    @inproceedings{2b318aa9297d458eb5d2c0a29bfb4b8e,
    title = "Alphastar: An evolutionary computation perspective",
    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.",
    keywords = "Co-evolution, Lamarckian evolution, Quality diversity",
    author = "Kai Arulkumaran and Antoine Cully and Julian Togelius",
    year = "2019",
    month = "7",
    day = "13",
    doi = "10.1145/3319619.3321894",
    language = "English (US)",
    series = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",
    publisher = "Association for Computing Machinery, Inc",
    pages = "314--315",
    booktitle = "GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion",

    }

    TY - GEN

    T1 - Alphastar

    T2 - An evolutionary computation perspective

    AU - Arulkumaran, Kai

    AU - Cully, Antoine

    AU - Togelius, Julian

    PY - 2019/7/13

    Y1 - 2019/7/13

    N2 - 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.

    AB - 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.

    KW - Co-evolution

    KW - Lamarckian evolution

    KW - Quality diversity

    UR - http://www.scopus.com/inward/record.url?scp=85070622576&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85070622576&partnerID=8YFLogxK

    U2 - 10.1145/3319619.3321894

    DO - 10.1145/3319619.3321894

    M3 - Conference contribution

    AN - SCOPUS:85070622576

    T3 - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

    SP - 314

    EP - 315

    BT - GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion

    PB - Association for Computing Machinery, Inc

    ER -