Evolving levels for Super Mario Bros using grammatical evolution

Noor Shaker, Miguel Nicolau, Georgios N. Yannakakis, Julian Togelius, Michael O'Neill

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

    Abstract

    This paper presents the use of design grammars to evolve playable 2D platform levels through grammatical evolution (GE). Representing levels using design grammars allows simple encoding of important level design constraints, and allows remarkably compact descriptions of large spaces of levels. The expressive range of the GE-based level generator is analyzed and quantitatively compared to other feature-based and the original level generators by means of aesthetic and similarity based measures. The analysis reveals strengths and shortcomings of each generator and provides a general framework for comparing content generated by different generators. The approach presented can be used as an assistive tool by game designers to compare and analyze generators' capabilities within the same game genre.

    Original languageEnglish (US)
    Title of host publication2012 IEEE Conference on Computational Intelligence and Games, CIG 2012
    Pages304-311
    Number of pages8
    DOIs
    StatePublished - 2012
    Event2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012 - Granada, Spain
    Duration: Sep 11 2012Sep 14 2012

    Other

    Other2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012
    CountrySpain
    CityGranada
    Period9/11/129/14/12

    ASJC Scopus subject areas

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

    Cite this

    Shaker, N., Nicolau, M., Yannakakis, G. N., Togelius, J., & O'Neill, M. (2012). Evolving levels for Super Mario Bros using grammatical evolution. In 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012 (pp. 304-311). [6374170] https://doi.org/10.1109/CIG.2012.6374170

    Evolving levels for Super Mario Bros using grammatical evolution. / Shaker, Noor; Nicolau, Miguel; Yannakakis, Georgios N.; Togelius, Julian; O'Neill, Michael.

    2012 IEEE Conference on Computational Intelligence and Games, CIG 2012. 2012. p. 304-311 6374170.

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

    Shaker, N, Nicolau, M, Yannakakis, GN, Togelius, J & O'Neill, M 2012, Evolving levels for Super Mario Bros using grammatical evolution. in 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012., 6374170, pp. 304-311, 2012 IEEE International Conference on Computational Intelligence and Games, CIG 2012, Granada, Spain, 9/11/12. https://doi.org/10.1109/CIG.2012.6374170
    Shaker N, Nicolau M, Yannakakis GN, Togelius J, O'Neill M. Evolving levels for Super Mario Bros using grammatical evolution. In 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012. 2012. p. 304-311. 6374170 https://doi.org/10.1109/CIG.2012.6374170
    Shaker, Noor ; Nicolau, Miguel ; Yannakakis, Georgios N. ; Togelius, Julian ; O'Neill, Michael. / Evolving levels for Super Mario Bros using grammatical evolution. 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012. 2012. pp. 304-311
    @inproceedings{2b32abb38c18471f85976d3f7953b14a,
    title = "Evolving levels for Super Mario Bros using grammatical evolution",
    abstract = "This paper presents the use of design grammars to evolve playable 2D platform levels through grammatical evolution (GE). Representing levels using design grammars allows simple encoding of important level design constraints, and allows remarkably compact descriptions of large spaces of levels. The expressive range of the GE-based level generator is analyzed and quantitatively compared to other feature-based and the original level generators by means of aesthetic and similarity based measures. The analysis reveals strengths and shortcomings of each generator and provides a general framework for comparing content generated by different generators. The approach presented can be used as an assistive tool by game designers to compare and analyze generators' capabilities within the same game genre.",
    author = "Noor Shaker and Miguel Nicolau and Yannakakis, {Georgios N.} and Julian Togelius and Michael O'Neill",
    year = "2012",
    doi = "10.1109/CIG.2012.6374170",
    language = "English (US)",
    isbn = "9781467311922",
    pages = "304--311",
    booktitle = "2012 IEEE Conference on Computational Intelligence and Games, CIG 2012",

    }

    TY - GEN

    T1 - Evolving levels for Super Mario Bros using grammatical evolution

    AU - Shaker, Noor

    AU - Nicolau, Miguel

    AU - Yannakakis, Georgios N.

    AU - Togelius, Julian

    AU - O'Neill, Michael

    PY - 2012

    Y1 - 2012

    N2 - This paper presents the use of design grammars to evolve playable 2D platform levels through grammatical evolution (GE). Representing levels using design grammars allows simple encoding of important level design constraints, and allows remarkably compact descriptions of large spaces of levels. The expressive range of the GE-based level generator is analyzed and quantitatively compared to other feature-based and the original level generators by means of aesthetic and similarity based measures. The analysis reveals strengths and shortcomings of each generator and provides a general framework for comparing content generated by different generators. The approach presented can be used as an assistive tool by game designers to compare and analyze generators' capabilities within the same game genre.

    AB - This paper presents the use of design grammars to evolve playable 2D platform levels through grammatical evolution (GE). Representing levels using design grammars allows simple encoding of important level design constraints, and allows remarkably compact descriptions of large spaces of levels. The expressive range of the GE-based level generator is analyzed and quantitatively compared to other feature-based and the original level generators by means of aesthetic and similarity based measures. The analysis reveals strengths and shortcomings of each generator and provides a general framework for comparing content generated by different generators. The approach presented can be used as an assistive tool by game designers to compare and analyze generators' capabilities within the same game genre.

    UR - http://www.scopus.com/inward/record.url?scp=84871946566&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84871946566&partnerID=8YFLogxK

    U2 - 10.1109/CIG.2012.6374170

    DO - 10.1109/CIG.2012.6374170

    M3 - Conference contribution

    SN - 9781467311922

    SP - 304

    EP - 311

    BT - 2012 IEEE Conference on Computational Intelligence and Games, CIG 2012

    ER -