Imitating human playing styles in Super Mario Bros

Juan Ortega, Noor Shaker, Julian Togelius, Georgios N. Yannakakis

    Research output: Contribution to journalArticlepeer-review


    We describe and compare several methods for generating game character controllers that mimic the playing style of a particular human player, or of a population of human players, across video game levels. Similarity in playing style is measured through an evaluation framework, that compares the play trace of one or several human players with the punctuated play trace of an AI player. The methods that are compared are either hand-coded, direct (based on supervised learning) or indirect (based on maximising a similarity measure). We find that a method based on neuroevolution performs best both in terms of the instrumental similarity measure and in phenomenological evaluation by human spectators. A version of the classic platform game " Super Mario Bros" is used as the testbed game in this study but the methods are applicable to other games that are based on character movement in space.

    Original languageEnglish (US)
    Pages (from-to)93-104
    Number of pages12
    JournalEntertainment Computing
    Issue number2
    StatePublished - Apr 2013


    • Behaviour cloning
    • Behaviour imitation
    • Dynamic scripting
    • Game AI
    • Imitation learning
    • Neuroevolution

    ASJC Scopus subject areas

    • Software
    • Human-Computer Interaction


    Dive into the research topics of 'Imitating human playing styles in Super Mario Bros'. Together they form a unique fingerprint.

    Cite this