Super Mario evolution

Julian Togelius, Sergey Karakovskiy, Jan Koutník, Jürgen Schmidhuber

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

69 Scopus citations

Abstract

We introduce a new reinforcement learning benchmark based on the classic platform game Super Mario Bros. The benchmark has a high-dimensional input space, and achieving a good score requires sophisticated and varied strategies. However, it has tunable difficulty, and at the lowest difficulty setting decent score can be achieved using rudimentary strategies and a small fraction of the input space. To investigate the properties of the benchmark, we evolve neural network-based controllers using different network architectures and input spaces. We show that it is relatively easy to learn basic strategies capable of clearing individual levels of low difficulty, but that these controllers have problems with generalization to unseen levels and with taking larger parts of the input space into account. A number of directions worth exploring for learning better-performing strategies are discussed. ©2009 IEEE.
Original languageEnglish (US)
Title of host publicationCIG2009 - 2009 IEEE Symposium on Computational Intelligence and Games
Pages156-161
Number of pages6
DOIs
StatePublished - Dec 14 2009
Externally publishedYes

Fingerprint

Dive into the research topics of 'Super Mario evolution'. Together they form a unique fingerprint.

Cite this