• DocumentCode
    1454426
  • Title

    The Mario AI Benchmark and Competitions

  • Author

    Karakovskiy, Sergey ; Togelius, Julian

  • Author_Institution
    St. Petersburg State Univ., St. Petersburg, Russia
  • Volume
    4
  • Issue
    1
  • fYear
    2012
  • fDate
    3/1/2012 12:00:00 AM
  • Firstpage
    55
  • Lastpage
    67
  • Abstract
    This paper describes the Mario AI benchmark, a game-based benchmark for reinforcement learning algorithms and game AI techniques developed by the authors. The benchmark is based on a public domain clone of Nintendo´s classic platform game Super Mario Bros, and completely open source. During the last two years, the benchmark has been used in a number of competitions associated with international conferences, and researchers and students from around the world have contributed diverse solutions to try to beat the benchmark. The paper summarizes these contributions, gives an overview of the state of the art in Mario-playing AIs, and chronicles the development of the benchmark. This paper is intended as the definitive point of reference for those using the benchmark for research or teaching.
  • Keywords
    computer games; learning (artificial intelligence); Mario AI benchmark; Mario AI competitions; Super Mario Bros; game based benchmark; international conferences; reinforcement learning algorithms; Artificial intelligence; Benchmark testing; Games; Generators; Humans; Java; Software; Benchmarking; competitions; game AI; reinforcement learning;
  • fLanguage
    English
  • Journal_Title
    Computational Intelligence and AI in Games, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1943-068X
  • Type

    jour

  • DOI
    10.1109/TCIAIG.2012.2188528
  • Filename
    6156425