Evolving behaviour trees for the Mario AI competition using grammatical evolution
Date:
2011-04-27
Recommended citation:
Perez, Diego, Nicolau, Miguel, O'Neill, Michael, Brabazon, Anthony
: Evolving behaviour trees for the Mario AI competition using grammatical evolution. EvoGAMES 2011 3rd European Event on Bio-inspired Algorithms in Games in EvoApplications 2011, Torino, Italy, April, 2011. 2011-04-27.
Abstract:
This paper investigates the applicability of Genetic Programming type systems to dynamic game environments. Grammatical Evolution was used to evolve Behaviour Trees, in order to create controllers for the Mario AI Benchmark. The results obtained reinforce the applicability of evolutionary programming systems to the development of artificial intelligence in games, and in dynamic systems in general, illustrating their viability as an alternative to more standard AI techniques.
Funding Details:
Science Foundation Ireland
Conference Details:
EvoGAMES 2011 3rd European Event on Bio-inspired Algorithms in Games in EvoApplications 2011, Torino, Italy, April, 2011
Type of material:
Conference Publication
Publisher:
Springer
Copyright (published version):
2011 Springer
Rights statement:
The final publication is available at springerlink.com
Is part of:
Di Chio, C. et al. [eds.]. Applications of Evolutionary Computation EvoApplications 2011: EvoCOMPLEX, EvoGAMES, EvoIASP, EvoINTELLIGENCE, EvoNUM, and EvoSTOC, Torino, Italy, April 27-29, 2011, Proceedings, Part I
ISBN:
978-3-642-20524-8
Status of item:
Peer reviewed
Language:
en
Availability:
Full text available
Available:
2012-03-08T14:44:45Z
Show full item record
Files in this item
This item appears in the following Collection(s)
This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.
If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.
RSS