Autoencoder and evolutionary algorithm for level generation in lode runner

Sarjak Thakkar, Changxing Cao, Lifan Wang, Tae Jong Choi, Julian Togelius

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

    Abstract

    Procedural content generation can be used to create arbitrarily large amounts of game levels automatically, but traditionally the PCG algorithms needed to be developed or adapted for each game manually. Procedural Content Generation via Machine Learning (PCGML) harnesses the power of machine learning to semi-automate the development of PCG solutions, training on existing game content so as to create new content from the trained models. One of the machine learning techniques that have been suggested for this purpose is the autoencoder. However, very limited work has been done to explore the potential of autoencoders for PCGML. In this paper, we train autoencoders on levels for the platform game Lode Runner, and use them to generate levels. Compared to previous work, we use a multi-channel approach to represent content in full fidelity, and we compare standard and variational autoencoders. We also evolve the values of the hidden layer of trained autoencoders in order to find levels with desired properties.

    Original languageEnglish (US)
    Title of host publicationIEEE Conference on Games 2019, CoG 2019
    PublisherIEEE Computer Society
    ISBN (Electronic)9781728118840
    DOIs
    StatePublished - Aug 2019
    Event2019 IEEE Conference on Games, CoG 2019 - London, United Kingdom
    Duration: Aug 20 2019Aug 23 2019

    Publication series

    NameIEEE Conference on Computatonal Intelligence and Games, CIG
    Volume2019-August
    ISSN (Print)2325-4270
    ISSN (Electronic)2325-4289

    Conference

    Conference2019 IEEE Conference on Games, CoG 2019
    CountryUnited Kingdom
    CityLondon
    Period8/20/198/23/19

    Fingerprint

    Evolutionary algorithms
    Learning systems

    ASJC Scopus subject areas

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

    Cite this

    Thakkar, S., Cao, C., Wang, L., Choi, T. J., & Togelius, J. (2019). Autoencoder and evolutionary algorithm for level generation in lode runner. In IEEE Conference on Games 2019, CoG 2019 [8848076] (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2019-August). IEEE Computer Society. https://doi.org/10.1109/CIG.2019.8848076

    Autoencoder and evolutionary algorithm for level generation in lode runner. / Thakkar, Sarjak; Cao, Changxing; Wang, Lifan; Choi, Tae Jong; Togelius, Julian.

    IEEE Conference on Games 2019, CoG 2019. IEEE Computer Society, 2019. 8848076 (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2019-August).

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

    Thakkar, S, Cao, C, Wang, L, Choi, TJ & Togelius, J 2019, Autoencoder and evolutionary algorithm for level generation in lode runner. in IEEE Conference on Games 2019, CoG 2019., 8848076, IEEE Conference on Computatonal Intelligence and Games, CIG, vol. 2019-August, IEEE Computer Society, 2019 IEEE Conference on Games, CoG 2019, London, United Kingdom, 8/20/19. https://doi.org/10.1109/CIG.2019.8848076
    Thakkar S, Cao C, Wang L, Choi TJ, Togelius J. Autoencoder and evolutionary algorithm for level generation in lode runner. In IEEE Conference on Games 2019, CoG 2019. IEEE Computer Society. 2019. 8848076. (IEEE Conference on Computatonal Intelligence and Games, CIG). https://doi.org/10.1109/CIG.2019.8848076
    Thakkar, Sarjak ; Cao, Changxing ; Wang, Lifan ; Choi, Tae Jong ; Togelius, Julian. / Autoencoder and evolutionary algorithm for level generation in lode runner. IEEE Conference on Games 2019, CoG 2019. IEEE Computer Society, 2019. (IEEE Conference on Computatonal Intelligence and Games, CIG).
    @inproceedings{d79cf030afae4074ad028800c066b2a9,
    title = "Autoencoder and evolutionary algorithm for level generation in lode runner",
    abstract = "Procedural content generation can be used to create arbitrarily large amounts of game levels automatically, but traditionally the PCG algorithms needed to be developed or adapted for each game manually. Procedural Content Generation via Machine Learning (PCGML) harnesses the power of machine learning to semi-automate the development of PCG solutions, training on existing game content so as to create new content from the trained models. One of the machine learning techniques that have been suggested for this purpose is the autoencoder. However, very limited work has been done to explore the potential of autoencoders for PCGML. In this paper, we train autoencoders on levels for the platform game Lode Runner, and use them to generate levels. Compared to previous work, we use a multi-channel approach to represent content in full fidelity, and we compare standard and variational autoencoders. We also evolve the values of the hidden layer of trained autoencoders in order to find levels with desired properties.",
    author = "Sarjak Thakkar and Changxing Cao and Lifan Wang and Choi, {Tae Jong} and Julian Togelius",
    year = "2019",
    month = "8",
    doi = "10.1109/CIG.2019.8848076",
    language = "English (US)",
    series = "IEEE Conference on Computatonal Intelligence and Games, CIG",
    publisher = "IEEE Computer Society",
    booktitle = "IEEE Conference on Games 2019, CoG 2019",

    }

    TY - GEN

    T1 - Autoencoder and evolutionary algorithm for level generation in lode runner

    AU - Thakkar, Sarjak

    AU - Cao, Changxing

    AU - Wang, Lifan

    AU - Choi, Tae Jong

    AU - Togelius, Julian

    PY - 2019/8

    Y1 - 2019/8

    N2 - Procedural content generation can be used to create arbitrarily large amounts of game levels automatically, but traditionally the PCG algorithms needed to be developed or adapted for each game manually. Procedural Content Generation via Machine Learning (PCGML) harnesses the power of machine learning to semi-automate the development of PCG solutions, training on existing game content so as to create new content from the trained models. One of the machine learning techniques that have been suggested for this purpose is the autoencoder. However, very limited work has been done to explore the potential of autoencoders for PCGML. In this paper, we train autoencoders on levels for the platform game Lode Runner, and use them to generate levels. Compared to previous work, we use a multi-channel approach to represent content in full fidelity, and we compare standard and variational autoencoders. We also evolve the values of the hidden layer of trained autoencoders in order to find levels with desired properties.

    AB - Procedural content generation can be used to create arbitrarily large amounts of game levels automatically, but traditionally the PCG algorithms needed to be developed or adapted for each game manually. Procedural Content Generation via Machine Learning (PCGML) harnesses the power of machine learning to semi-automate the development of PCG solutions, training on existing game content so as to create new content from the trained models. One of the machine learning techniques that have been suggested for this purpose is the autoencoder. However, very limited work has been done to explore the potential of autoencoders for PCGML. In this paper, we train autoencoders on levels for the platform game Lode Runner, and use them to generate levels. Compared to previous work, we use a multi-channel approach to represent content in full fidelity, and we compare standard and variational autoencoders. We also evolve the values of the hidden layer of trained autoencoders in order to find levels with desired properties.

    UR - http://www.scopus.com/inward/record.url?scp=85073109349&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85073109349&partnerID=8YFLogxK

    U2 - 10.1109/CIG.2019.8848076

    DO - 10.1109/CIG.2019.8848076

    M3 - Conference contribution

    AN - SCOPUS:85073109349

    T3 - IEEE Conference on Computatonal Intelligence and Games, CIG

    BT - IEEE Conference on Games 2019, CoG 2019

    PB - IEEE Computer Society

    ER -