Publication:
Learning Levels of Mario AI Using Genetic Algorithms

Thumbnail Image
Identifiers
URI: https://hdl.handle.net/10016/22309
ISSN: 0302-9743
ISBN: 978-3-319-24597-3 (Print)
ISBN: 978-3-319-24598-0 (Online)
DOI: 10.1007/978-3-319-24598-0_24
UXXI: CC/0000024141
Files
learning_AAI_2015_ps.pdf (627.92 KB)
Publication date
2015-11-11
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
This paper introduces an approach based on Genetic Algorithms to learn levels from the Mario AI simulator, based on the Infinite Mario Bros. game (which is, at the same time, based on the Super Mario World game from Nintendo). In this approach, an autonomous agent playing Mario is able to learn a sequence of actions in order to maximize the score, not looking at the current state of the game at each time. Different parameters for the Genetic Algorithm are explored, and two different stages are executed: in the first, domain independent genetic operators are used; while in the second knowledge about the domain is incorporated to these operators in order to improve the results. Results are encouraging, as Mario is able to complete very difficult levels full of enemies, resembling the behavior of an expert human player.
Description
This procceding at: 16th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2015, took place at: November 9-12, 2015, in Albacete, Spain.
Keywords
Mario AI, Games, Genetic algorithms, Learning.
Bibliographic citation
Advances in Artificial Intelligence, LNCS 9422 (2015) pp. 267-277.
Collections
DI - GCERN - Capítulos de Monografías
Proyectos FOS (2019-2020)