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.
|Title of host publication
|2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008
|Number of pages
|Published - Dec 1 2008