Adaptive game level creation through rank-based interactive evolution

Antonios Liapis, Hector P. Martinez, Julian Togelius, Georgios N. Yannakakis

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

    Abstract

    This paper introduces Rank-based Interactive Evolution (RIE) which is an alternative to interactive evolution driven by computational models of user preferences to generate personalized content. In RIE, the computational models are adapted to the preferences of users which, in turn, are used as fitness functions for the optimization of the generated content. The preference models are built via ranking-based preference learning, while the content is generated via evolutionary search. The proposed method is evaluated on the creation of strategy game maps, and its performance is tested using artificial agents. Results suggest that RIE is both faster and more robust than standard interactive evolution and outperforms other state-of-the-art interactive evolution approaches.

    Original languageEnglish (US)
    Title of host publication2013 IEEE Conference on Computational Intelligence in Games, CIG 2013
    DOIs
    StatePublished - 2013
    Event2013 IEEE Conference on Computational Intelligence in Games, CIG 2013 - Niagara Falls, ON, Canada
    Duration: Aug 11 2013Aug 13 2013

    Other

    Other2013 IEEE Conference on Computational Intelligence in Games, CIG 2013
    CountryCanada
    CityNiagara Falls, ON
    Period8/11/138/13/13

    ASJC Scopus subject areas

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

    Cite this

    Liapis, A., Martinez, H. P., Togelius, J., & Yannakakis, G. N. (2013). Adaptive game level creation through rank-based interactive evolution. In 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013 [6633651] https://doi.org/10.1109/CIG.2013.6633651

    Adaptive game level creation through rank-based interactive evolution. / Liapis, Antonios; Martinez, Hector P.; Togelius, Julian; Yannakakis, Georgios N.

    2013 IEEE Conference on Computational Intelligence in Games, CIG 2013. 2013. 6633651.

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

    Liapis, A, Martinez, HP, Togelius, J & Yannakakis, GN 2013, Adaptive game level creation through rank-based interactive evolution. in 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013., 6633651, 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013, Niagara Falls, ON, Canada, 8/11/13. https://doi.org/10.1109/CIG.2013.6633651
    Liapis A, Martinez HP, Togelius J, Yannakakis GN. Adaptive game level creation through rank-based interactive evolution. In 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013. 2013. 6633651 https://doi.org/10.1109/CIG.2013.6633651
    Liapis, Antonios ; Martinez, Hector P. ; Togelius, Julian ; Yannakakis, Georgios N. / Adaptive game level creation through rank-based interactive evolution. 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013. 2013.
    @inproceedings{8717c52be7b5498fb5f20e7ec3a6b748,
    title = "Adaptive game level creation through rank-based interactive evolution",
    abstract = "This paper introduces Rank-based Interactive Evolution (RIE) which is an alternative to interactive evolution driven by computational models of user preferences to generate personalized content. In RIE, the computational models are adapted to the preferences of users which, in turn, are used as fitness functions for the optimization of the generated content. The preference models are built via ranking-based preference learning, while the content is generated via evolutionary search. The proposed method is evaluated on the creation of strategy game maps, and its performance is tested using artificial agents. Results suggest that RIE is both faster and more robust than standard interactive evolution and outperforms other state-of-the-art interactive evolution approaches.",
    author = "Antonios Liapis and Martinez, {Hector P.} and Julian Togelius and Yannakakis, {Georgios N.}",
    year = "2013",
    doi = "10.1109/CIG.2013.6633651",
    language = "English (US)",
    isbn = "9781467353113",
    booktitle = "2013 IEEE Conference on Computational Intelligence in Games, CIG 2013",

    }

    TY - GEN

    T1 - Adaptive game level creation through rank-based interactive evolution

    AU - Liapis, Antonios

    AU - Martinez, Hector P.

    AU - Togelius, Julian

    AU - Yannakakis, Georgios N.

    PY - 2013

    Y1 - 2013

    N2 - This paper introduces Rank-based Interactive Evolution (RIE) which is an alternative to interactive evolution driven by computational models of user preferences to generate personalized content. In RIE, the computational models are adapted to the preferences of users which, in turn, are used as fitness functions for the optimization of the generated content. The preference models are built via ranking-based preference learning, while the content is generated via evolutionary search. The proposed method is evaluated on the creation of strategy game maps, and its performance is tested using artificial agents. Results suggest that RIE is both faster and more robust than standard interactive evolution and outperforms other state-of-the-art interactive evolution approaches.

    AB - This paper introduces Rank-based Interactive Evolution (RIE) which is an alternative to interactive evolution driven by computational models of user preferences to generate personalized content. In RIE, the computational models are adapted to the preferences of users which, in turn, are used as fitness functions for the optimization of the generated content. The preference models are built via ranking-based preference learning, while the content is generated via evolutionary search. The proposed method is evaluated on the creation of strategy game maps, and its performance is tested using artificial agents. Results suggest that RIE is both faster and more robust than standard interactive evolution and outperforms other state-of-the-art interactive evolution approaches.

    UR - http://www.scopus.com/inward/record.url?scp=84892404742&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84892404742&partnerID=8YFLogxK

    U2 - 10.1109/CIG.2013.6633651

    DO - 10.1109/CIG.2013.6633651

    M3 - Conference contribution

    AN - SCOPUS:84892404742

    SN - 9781467353113

    BT - 2013 IEEE Conference on Computational Intelligence in Games, CIG 2013

    ER -