A scalable neural network architecture for board games

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

4 Scopus citations

Abstract

This paper proposes to use Multi-dimensional Recurrent Neural Networks (MDRNNs) as a way to overcome one of the key problems in flexible-size board games: scalability. We show why this architecture is well suited to the domain and how it can be successfully trained to play those games, even without any domain-specific knowledge. We find that performance on small boards correlates well with perform~nce on large ones, and that this property holds for networks tramedby either evolution or coevolution. ©2008 IEEE.
Original languageEnglish (US)
Title of host publication2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
Pages357-364
Number of pages8
DOIs
StatePublished - Dec 1 2008
Externally publishedYes

Fingerprint

Dive into the research topics of 'A scalable neural network architecture for board games'. Together they form a unique fingerprint.

Cite this