Neuroevolutionary constrained optimization for content creation

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

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

    Abstract

    This paper presents a constraint-based procedural content generation (PCG) framework used for the creation of novel and high-performing content. Specifically, we examine the efficiency of the framework for the creation of spaceship design (hull shape and spaceship attributes such as weapon and thruster types and topologies) independently of game physics and steering strategies. According to the proposed framework, the designer picks a set of requirements for the spaceship that a constrained optimizer attempts to satisfy. The constraint satisfaction approach followed is based on neuroevolution; Compositional Pattern-Producing Networks (CPPNs) which represent the spaceship's design are trained via a constraint-based evolutionary algorithm. Results obtained in a number of evolutionary runs using a set of constraints and objectives show that the generated spaceships perform well in movement, combat and survival tasks and are also visually appealing.

    Original languageEnglish (US)
    Title of host publication2011 IEEE Conference on Computational Intelligence and Games, CIG 2011
    Pages71-78
    Number of pages8
    DOIs
    StatePublished - 2011
    Event2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011 - Seoul, Korea, Republic of
    Duration: Aug 31 2011Sep 3 2011

    Other

    Other2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011
    CountryKorea, Republic of
    CitySeoul
    Period8/31/119/3/11

    Fingerprint

    Constrained optimization
    Evolutionary algorithms
    Physics
    Topology

    ASJC Scopus subject areas

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

    Cite this

    Liapis, A., Yannakakis, G. N., & Togelius, J. (2011). Neuroevolutionary constrained optimization for content creation. In 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011 (pp. 71-78). [6031991] https://doi.org/10.1109/CIG.2011.6031991

    Neuroevolutionary constrained optimization for content creation. / Liapis, Antonios; Yannakakis, Georgios N.; Togelius, Julian.

    2011 IEEE Conference on Computational Intelligence and Games, CIG 2011. 2011. p. 71-78 6031991.

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

    Liapis, A, Yannakakis, GN & Togelius, J 2011, Neuroevolutionary constrained optimization for content creation. in 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011., 6031991, pp. 71-78, 2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011, Seoul, Korea, Republic of, 8/31/11. https://doi.org/10.1109/CIG.2011.6031991
    Liapis A, Yannakakis GN, Togelius J. Neuroevolutionary constrained optimization for content creation. In 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011. 2011. p. 71-78. 6031991 https://doi.org/10.1109/CIG.2011.6031991
    Liapis, Antonios ; Yannakakis, Georgios N. ; Togelius, Julian. / Neuroevolutionary constrained optimization for content creation. 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011. 2011. pp. 71-78
    @inproceedings{c33245c2dca141f1928d4765005516b3,
    title = "Neuroevolutionary constrained optimization for content creation",
    abstract = "This paper presents a constraint-based procedural content generation (PCG) framework used for the creation of novel and high-performing content. Specifically, we examine the efficiency of the framework for the creation of spaceship design (hull shape and spaceship attributes such as weapon and thruster types and topologies) independently of game physics and steering strategies. According to the proposed framework, the designer picks a set of requirements for the spaceship that a constrained optimizer attempts to satisfy. The constraint satisfaction approach followed is based on neuroevolution; Compositional Pattern-Producing Networks (CPPNs) which represent the spaceship's design are trained via a constraint-based evolutionary algorithm. Results obtained in a number of evolutionary runs using a set of constraints and objectives show that the generated spaceships perform well in movement, combat and survival tasks and are also visually appealing.",
    author = "Antonios Liapis and Yannakakis, {Georgios N.} and Julian Togelius",
    year = "2011",
    doi = "10.1109/CIG.2011.6031991",
    language = "English (US)",
    isbn = "9781457700095",
    pages = "71--78",
    booktitle = "2011 IEEE Conference on Computational Intelligence and Games, CIG 2011",

    }

    TY - GEN

    T1 - Neuroevolutionary constrained optimization for content creation

    AU - Liapis, Antonios

    AU - Yannakakis, Georgios N.

    AU - Togelius, Julian

    PY - 2011

    Y1 - 2011

    N2 - This paper presents a constraint-based procedural content generation (PCG) framework used for the creation of novel and high-performing content. Specifically, we examine the efficiency of the framework for the creation of spaceship design (hull shape and spaceship attributes such as weapon and thruster types and topologies) independently of game physics and steering strategies. According to the proposed framework, the designer picks a set of requirements for the spaceship that a constrained optimizer attempts to satisfy. The constraint satisfaction approach followed is based on neuroevolution; Compositional Pattern-Producing Networks (CPPNs) which represent the spaceship's design are trained via a constraint-based evolutionary algorithm. Results obtained in a number of evolutionary runs using a set of constraints and objectives show that the generated spaceships perform well in movement, combat and survival tasks and are also visually appealing.

    AB - This paper presents a constraint-based procedural content generation (PCG) framework used for the creation of novel and high-performing content. Specifically, we examine the efficiency of the framework for the creation of spaceship design (hull shape and spaceship attributes such as weapon and thruster types and topologies) independently of game physics and steering strategies. According to the proposed framework, the designer picks a set of requirements for the spaceship that a constrained optimizer attempts to satisfy. The constraint satisfaction approach followed is based on neuroevolution; Compositional Pattern-Producing Networks (CPPNs) which represent the spaceship's design are trained via a constraint-based evolutionary algorithm. Results obtained in a number of evolutionary runs using a set of constraints and objectives show that the generated spaceships perform well in movement, combat and survival tasks and are also visually appealing.

    UR - http://www.scopus.com/inward/record.url?scp=80054030688&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=80054030688&partnerID=8YFLogxK

    U2 - 10.1109/CIG.2011.6031991

    DO - 10.1109/CIG.2011.6031991

    M3 - Conference contribution

    SN - 9781457700095

    SP - 71

    EP - 78

    BT - 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011

    ER -