Generating diverse opponents with multiobjective evolution

Alexandros Agapitos, Julian Togelius, Simon M. Lucas, Jürgen Schmidhuber, Andreas Konstantinidis

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

    Abstract

    For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers.

    Original languageEnglish (US)
    Title of host publication2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
    Pages135-142
    Number of pages8
    DOIs
    StatePublished - 2008
    Event2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 - Perth, WA, Australia
    Duration: Dec 15 2008Dec 18 2008

    Other

    Other2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
    CountryAustralia
    CityPerth, WA
    Period12/15/0812/18/08

    Fingerprint

    Controllers
    Genetic programming
    Evolutionary algorithms
    Artificial intelligence
    Experiments

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Human-Computer Interaction

    Cite this

    Agapitos, A., Togelius, J., Lucas, S. M., Schmidhuber, J., & Konstantinidis, A. (2008). Generating diverse opponents with multiobjective evolution. In 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 (pp. 135-142). [5035632] https://doi.org/10.1109/CIG.2008.5035632

    Generating diverse opponents with multiobjective evolution. / Agapitos, Alexandros; Togelius, Julian; Lucas, Simon M.; Schmidhuber, Jürgen; Konstantinidis, Andreas.

    2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. p. 135-142 5035632.

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

    Agapitos, A, Togelius, J, Lucas, SM, Schmidhuber, J & Konstantinidis, A 2008, Generating diverse opponents with multiobjective evolution. in 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008., 5035632, pp. 135-142, 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008, Perth, WA, Australia, 12/15/08. https://doi.org/10.1109/CIG.2008.5035632
    Agapitos A, Togelius J, Lucas SM, Schmidhuber J, Konstantinidis A. Generating diverse opponents with multiobjective evolution. In 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. p. 135-142. 5035632 https://doi.org/10.1109/CIG.2008.5035632
    Agapitos, Alexandros ; Togelius, Julian ; Lucas, Simon M. ; Schmidhuber, Jürgen ; Konstantinidis, Andreas. / Generating diverse opponents with multiobjective evolution. 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008. 2008. pp. 135-142
    @inproceedings{77e9948cf5f14555ba6432a8548acc21,
    title = "Generating diverse opponents with multiobjective evolution",
    abstract = "For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers.",
    author = "Alexandros Agapitos and Julian Togelius and Lucas, {Simon M.} and J{\"u}rgen Schmidhuber and Andreas Konstantinidis",
    year = "2008",
    doi = "10.1109/CIG.2008.5035632",
    language = "English (US)",
    isbn = "9781424429745",
    pages = "135--142",
    booktitle = "2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008",

    }

    TY - GEN

    T1 - Generating diverse opponents with multiobjective evolution

    AU - Agapitos, Alexandros

    AU - Togelius, Julian

    AU - Lucas, Simon M.

    AU - Schmidhuber, Jürgen

    AU - Konstantinidis, Andreas

    PY - 2008

    Y1 - 2008

    N2 - For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers.

    AB - For computational intelligence to be useful in creating game agent AI, we need to focus on creating interesting and believable agents rather than just learn to play the games well. To this end, we propose a way use multiobjective evolutionary algorithms to automatically create populations of Non-Player Characters (NPCs), such as opponents and collaborators that are interestingly diverse in behaviour space. Experiments 'are presented where a number of partially conflicting objectives are defined for racing game competitors, and multiobjective evolution of Genetic Programming-based controllers yield pareto fronts of interesting controllers.

    UR - http://www.scopus.com/inward/record.url?scp=70349300413&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70349300413&partnerID=8YFLogxK

    U2 - 10.1109/CIG.2008.5035632

    DO - 10.1109/CIG.2008.5035632

    M3 - Conference contribution

    SN - 9781424429745

    SP - 135

    EP - 142

    BT - 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008

    ER -