Skip to search boxSkip to navigationSkip to main content

The Mario AI Benchmark and Competitions

  • Sergey Karakovskiy
    ,
  • Julian Togelius
Research Output:
Journal Article or Conference Article in Journal
Journal article
Peer-review

Publication Information

Output type

Research Output:
Journal Article or Conference Article in Journal
Journal article
Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 55 - 67

Journal (Volume, Issue Number)

I E E E Transactions on Computational Intelligence and A I in Games (Volume 4, Issue 1)

Publication milestones

  • Published - 2012

Publication status

Published - 2012

ISSN

1943-068X

Publication IDs

  • Scopus: 84858967765

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.

Publication metrics

PlumX

Captures
95
Citations
132