Towards multiobjective procedural map generation

Julian Togelius, Mike Preuss, Georgios N. Yannakakis

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

    Abstract

    A search-based procedural content generation (SBPCG) algorithm for strategy game maps is proposed. Two representations for strategy game maps are devised, along with a number of objectives relating to predicted player experience. A multiobjective evolutionary algorithm is used for searching the space of maps for candidates that satisfy pairs of these objectives. As the objectives are inherently partially conicting, the algorithm generates Pareto fronts showing how these objectives can be balanced. Such fronts are argued to be a valuable tool for designers looking to balance various design needs. Choosing appropriate points (manually or automatically) on the Pareto fronts, maps can be found that exhibit good map design according to specified criteria, and could either be used directly in e.g. an RTS game or form the basis for further human design.

    Original languageEnglish (US)
    Title of host publicationWorkshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games
    DOIs
    StatePublished - 2010
    EventWorkshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 2010 Foundations of Digital Games Conference - Monterey, CA, United States
    Duration: Jun 18 2010Jun 18 2010

    Other

    OtherWorkshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 2010 Foundations of Digital Games Conference
    CountryUnited States
    CityMonterey, CA
    Period6/18/106/18/10

    Fingerprint

    Evolutionary algorithms

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Human-Computer Interaction
    • Software

    Cite this

    Togelius, J., Preuss, M., & Yannakakis, G. N. (2010). Towards multiobjective procedural map generation. In Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games [3] https://doi.org/10.1145/1814256.1814259

    Towards multiobjective procedural map generation. / Togelius, Julian; Preuss, Mike; Yannakakis, Georgios N.

    Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games. 2010. 3.

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

    Togelius, J, Preuss, M & Yannakakis, GN 2010, Towards multiobjective procedural map generation. in Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games., 3, Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 2010 Foundations of Digital Games Conference, Monterey, CA, United States, 6/18/10. https://doi.org/10.1145/1814256.1814259
    Togelius J, Preuss M, Yannakakis GN. Towards multiobjective procedural map generation. In Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games. 2010. 3 https://doi.org/10.1145/1814256.1814259
    Togelius, Julian ; Preuss, Mike ; Yannakakis, Georgios N. / Towards multiobjective procedural map generation. Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games. 2010.
    @inproceedings{f9e2f626313a42059bf13aee8d8b55d4,
    title = "Towards multiobjective procedural map generation",
    abstract = "A search-based procedural content generation (SBPCG) algorithm for strategy game maps is proposed. Two representations for strategy game maps are devised, along with a number of objectives relating to predicted player experience. A multiobjective evolutionary algorithm is used for searching the space of maps for candidates that satisfy pairs of these objectives. As the objectives are inherently partially conicting, the algorithm generates Pareto fronts showing how these objectives can be balanced. Such fronts are argued to be a valuable tool for designers looking to balance various design needs. Choosing appropriate points (manually or automatically) on the Pareto fronts, maps can be found that exhibit good map design according to specified criteria, and could either be used directly in e.g. an RTS game or form the basis for further human design.",
    author = "Julian Togelius and Mike Preuss and Yannakakis, {Georgios N.}",
    year = "2010",
    doi = "10.1145/1814256.1814259",
    language = "English (US)",
    isbn = "9781450300230",
    booktitle = "Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games",

    }

    TY - GEN

    T1 - Towards multiobjective procedural map generation

    AU - Togelius, Julian

    AU - Preuss, Mike

    AU - Yannakakis, Georgios N.

    PY - 2010

    Y1 - 2010

    N2 - A search-based procedural content generation (SBPCG) algorithm for strategy game maps is proposed. Two representations for strategy game maps are devised, along with a number of objectives relating to predicted player experience. A multiobjective evolutionary algorithm is used for searching the space of maps for candidates that satisfy pairs of these objectives. As the objectives are inherently partially conicting, the algorithm generates Pareto fronts showing how these objectives can be balanced. Such fronts are argued to be a valuable tool for designers looking to balance various design needs. Choosing appropriate points (manually or automatically) on the Pareto fronts, maps can be found that exhibit good map design according to specified criteria, and could either be used directly in e.g. an RTS game or form the basis for further human design.

    AB - A search-based procedural content generation (SBPCG) algorithm for strategy game maps is proposed. Two representations for strategy game maps are devised, along with a number of objectives relating to predicted player experience. A multiobjective evolutionary algorithm is used for searching the space of maps for candidates that satisfy pairs of these objectives. As the objectives are inherently partially conicting, the algorithm generates Pareto fronts showing how these objectives can be balanced. Such fronts are argued to be a valuable tool for designers looking to balance various design needs. Choosing appropriate points (manually or automatically) on the Pareto fronts, maps can be found that exhibit good map design according to specified criteria, and could either be used directly in e.g. an RTS game or form the basis for further human design.

    UR - http://www.scopus.com/inward/record.url?scp=77954980239&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77954980239&partnerID=8YFLogxK

    U2 - 10.1145/1814256.1814259

    DO - 10.1145/1814256.1814259

    M3 - Conference contribution

    AN - SCOPUS:77954980239

    SN - 9781450300230

    BT - Workshop on Procedural Content Generation in Games, PC Games 2010, Co-located with the 5th International Conference on the Foundations of Digital Games

    ER -