2010 | OriginalPaper | Buchkapitel
Indirect Encoding of Neural Networks for Scalable Go
verfasst von : Jason Gauci, Kenneth O. Stanley
Erschienen in: Parallel Problem Solving from Nature, PPSN XI
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The game of Go has attracted much attention from the artificial intelligence community. A key feature of Go is that humans begin to learn on a small board, and then incrementally learn advanced strategies on larger boards. While some machine learning methods can also scale the board, they generally only focus on a subset of the board at one time. Neuroevolution algorithms particularly struggle with scalable Go because they are often directly encoded (i.e. a single gene maps to a single connection in the network). Thus this paper applies an
indirect encoding
to the problem of scalable Go that can evolve a solution to 5×5 Go and then
extrapolate
that solution to 7×7 Go and continue evolution. The scalable method is demonstrated to learn faster and ultimately discover better strategies than the same method trained on 7×7 Go directly from the start.