Talakat: Bullet hell generation through constrained map-elites

Ahmed Khalifa, Andrew Nealen, Scott Lee, Julian Togelius

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

    Abstract

    We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles. Levels are represented using a domain-specific description language, and search in the space defined by this language is performed by a novel variant of the Map-Elites algorithm which incorporates a feasible-infeasible approach to constraint satisfaction. Simulation-based evaluation is used to gauge the fitness of levels, using an agent based on best-first search. The performance of the agent can be tuned according to the two dimensions of strategy and dexterity, making it possible to search for level configurations that require a specific combination of both. As far as we know, this paper describes the first generator for this game genre, and includes several algorithmic innovations.

    Original languageEnglish (US)
    Title of host publicationGECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference
    PublisherAssociation for Computing Machinery, Inc
    Pages1047-1054
    Number of pages8
    ISBN (Electronic)9781450356183
    DOIs
    StatePublished - Jul 2 2018
    Event2018 Genetic and Evolutionary Computation Conference, GECCO 2018 - Kyoto, Japan
    Duration: Jul 15 2018Jul 19 2018

    Other

    Other2018 Genetic and Evolutionary Computation Conference, GECCO 2018
    CountryJapan
    CityKyoto
    Period7/15/187/19/18

    Fingerprint

    Projectiles
    Gages
    Innovation

    Keywords

    • Bullet Hell
    • Constraint Map-Elites
    • Description Language
    • Framework

    ASJC Scopus subject areas

    • Computer Science Applications
    • Software
    • Computational Theory and Mathematics

    Cite this

    Khalifa, A., Nealen, A., Lee, S., & Togelius, J. (2018). Talakat: Bullet hell generation through constrained map-elites. In GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference (pp. 1047-1054). Association for Computing Machinery, Inc. https://doi.org/10.1145/3205455.3205470

    Talakat : Bullet hell generation through constrained map-elites. / Khalifa, Ahmed; Nealen, Andrew; Lee, Scott; Togelius, Julian.

    GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, Inc, 2018. p. 1047-1054.

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

    Khalifa, A, Nealen, A, Lee, S & Togelius, J 2018, Talakat: Bullet hell generation through constrained map-elites. in GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, Inc, pp. 1047-1054, 2018 Genetic and Evolutionary Computation Conference, GECCO 2018, Kyoto, Japan, 7/15/18. https://doi.org/10.1145/3205455.3205470
    Khalifa A, Nealen A, Lee S, Togelius J. Talakat: Bullet hell generation through constrained map-elites. In GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, Inc. 2018. p. 1047-1054 https://doi.org/10.1145/3205455.3205470
    Khalifa, Ahmed ; Nealen, Andrew ; Lee, Scott ; Togelius, Julian. / Talakat : Bullet hell generation through constrained map-elites. GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, Inc, 2018. pp. 1047-1054
    @inproceedings{6d912bfd99404e9e9e41b0d10d0edc2b,
    title = "Talakat: Bullet hell generation through constrained map-elites",
    abstract = "We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles. Levels are represented using a domain-specific description language, and search in the space defined by this language is performed by a novel variant of the Map-Elites algorithm which incorporates a feasible-infeasible approach to constraint satisfaction. Simulation-based evaluation is used to gauge the fitness of levels, using an agent based on best-first search. The performance of the agent can be tuned according to the two dimensions of strategy and dexterity, making it possible to search for level configurations that require a specific combination of both. As far as we know, this paper describes the first generator for this game genre, and includes several algorithmic innovations.",
    keywords = "Bullet Hell, Constraint Map-Elites, Description Language, Framework",
    author = "Ahmed Khalifa and Andrew Nealen and Scott Lee and Julian Togelius",
    year = "2018",
    month = "7",
    day = "2",
    doi = "10.1145/3205455.3205470",
    language = "English (US)",
    pages = "1047--1054",
    booktitle = "GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference",
    publisher = "Association for Computing Machinery, Inc",

    }

    TY - GEN

    T1 - Talakat

    T2 - Bullet hell generation through constrained map-elites

    AU - Khalifa, Ahmed

    AU - Nealen, Andrew

    AU - Lee, Scott

    AU - Togelius, Julian

    PY - 2018/7/2

    Y1 - 2018/7/2

    N2 - We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles. Levels are represented using a domain-specific description language, and search in the space defined by this language is performed by a novel variant of the Map-Elites algorithm which incorporates a feasible-infeasible approach to constraint satisfaction. Simulation-based evaluation is used to gauge the fitness of levels, using an agent based on best-first search. The performance of the agent can be tuned according to the two dimensions of strategy and dexterity, making it possible to search for level configurations that require a specific combination of both. As far as we know, this paper describes the first generator for this game genre, and includes several algorithmic innovations.

    AB - We describe a search-based approach to generating new levels for bullet hell games, which are action games characterized by and requiring avoidance of a very large amount of projectiles. Levels are represented using a domain-specific description language, and search in the space defined by this language is performed by a novel variant of the Map-Elites algorithm which incorporates a feasible-infeasible approach to constraint satisfaction. Simulation-based evaluation is used to gauge the fitness of levels, using an agent based on best-first search. The performance of the agent can be tuned according to the two dimensions of strategy and dexterity, making it possible to search for level configurations that require a specific combination of both. As far as we know, this paper describes the first generator for this game genre, and includes several algorithmic innovations.

    KW - Bullet Hell

    KW - Constraint Map-Elites

    KW - Description Language

    KW - Framework

    UR - http://www.scopus.com/inward/record.url?scp=85050619254&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85050619254&partnerID=8YFLogxK

    U2 - 10.1145/3205455.3205470

    DO - 10.1145/3205455.3205470

    M3 - Conference contribution

    SP - 1047

    EP - 1054

    BT - GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference

    PB - Association for Computing Machinery, Inc

    ER -