Robust player imitation using multiobjective evolution

Niels Van Hoorn, Julian Togelius, Daan Wierstra, Jürgen Schmidhuber

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

    Abstract

    The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.

    Original languageEnglish (US)
    Title of host publication2009 IEEE Congress on Evolutionary Computation, CEC 2009
    Pages652-659
    Number of pages8
    DOIs
    StatePublished - 2009
    Event2009 IEEE Congress on Evolutionary Computation, CEC 2009 - Trondheim, Norway
    Duration: May 18 2009May 21 2009

    Other

    Other2009 IEEE Congress on Evolutionary Computation, CEC 2009
    CountryNorway
    CityTrondheim
    Period5/18/095/21/09

    Fingerprint

    Imitation
    Human Behavior
    Evolutionary algorithms
    Game
    Video Games
    Multi-objective Evolutionary Algorithm
    Fitness
    Sufficient
    Generalise
    Similarity
    Learning
    Context
    Human

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computational Theory and Mathematics
    • Theoretical Computer Science

    Cite this

    Van Hoorn, N., Togelius, J., Wierstra, D., & Schmidhuber, J. (2009). Robust player imitation using multiobjective evolution. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009 (pp. 652-659). [4983007] https://doi.org/10.1109/CEC.2009.4983007

    Robust player imitation using multiobjective evolution. / Van Hoorn, Niels; Togelius, Julian; Wierstra, Daan; Schmidhuber, Jürgen.

    2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 652-659 4983007.

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

    Van Hoorn, N, Togelius, J, Wierstra, D & Schmidhuber, J 2009, Robust player imitation using multiobjective evolution. in 2009 IEEE Congress on Evolutionary Computation, CEC 2009., 4983007, pp. 652-659, 2009 IEEE Congress on Evolutionary Computation, CEC 2009, Trondheim, Norway, 5/18/09. https://doi.org/10.1109/CEC.2009.4983007
    Van Hoorn N, Togelius J, Wierstra D, Schmidhuber J. Robust player imitation using multiobjective evolution. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 652-659. 4983007 https://doi.org/10.1109/CEC.2009.4983007
    Van Hoorn, Niels ; Togelius, Julian ; Wierstra, Daan ; Schmidhuber, Jürgen. / Robust player imitation using multiobjective evolution. 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. pp. 652-659
    @inproceedings{a0f89d5ea3a14e3baf987e3584cb4b35,
    title = "Robust player imitation using multiobjective evolution",
    abstract = "The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.",
    author = "{Van Hoorn}, Niels and Julian Togelius and Daan Wierstra and J{\"u}rgen Schmidhuber",
    year = "2009",
    doi = "10.1109/CEC.2009.4983007",
    language = "English (US)",
    isbn = "9781424429592",
    pages = "652--659",
    booktitle = "2009 IEEE Congress on Evolutionary Computation, CEC 2009",

    }

    TY - GEN

    T1 - Robust player imitation using multiobjective evolution

    AU - Van Hoorn, Niels

    AU - Togelius, Julian

    AU - Wierstra, Daan

    AU - Schmidhuber, Jürgen

    PY - 2009

    Y1 - 2009

    N2 - The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.

    AB - The problem of how to create NPC AI for videogames that believably imitates particular human players is addressed. Previous approaches to learning player behaviour is found to either not generalize well to new environments and noisy perceptions, or to not reproduce human behaviour in sufficient detail. It is proposed that better solutions to this problem can be built on multiobjective evolutionary algorithms, with objectives relating both to traditional progress-based fitness (playing the game well) and similarity to recorded human behaviour (behaving like the recorded player). This idea is explored in the context of a modern racing game.

    UR - http://www.scopus.com/inward/record.url?scp=70449890193&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70449890193&partnerID=8YFLogxK

    U2 - 10.1109/CEC.2009.4983007

    DO - 10.1109/CEC.2009.4983007

    M3 - Conference contribution

    SN - 9781424429592

    SP - 652

    EP - 659

    BT - 2009 IEEE Congress on Evolutionary Computation, CEC 2009

    ER -