A wavelet-based encoding for neuroevolution

Sjoerd Van Steenkiste, Jan Koutník, Kurt Driessens, Jürgen Schmidhuber

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

11 Scopus citations


A new indirect scheme for encoding neural network connection weights as sets of wavelet-domain coefficients is proposed in this paper. It exploits spatial regularities in the weight-space to reduce the gene-space dimension by considering the low-frequency wavelet coefficients only. The wavelet-based encoding builds on top of a frequency-domain encoding, but unlike when using a Fourier-type transform, it offers gene locality while preserving continuity of the genotype-phenotype mapping. We argue that this added property allows for more efficient evolutionary search and demonstrate this on the octopus-arm control task, where superior solutions were found in fewer generations. The scalability of the wavelet-based encoding is shown by evolving networks with many parameters to control game-playing agents in the Arcade Learning Environment.
Original languageEnglish (US)
Title of host publicationGECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference
PublisherAssociation for Computing Machinery, [email protected]
Number of pages8
ISBN (Print)9781450342063
StatePublished - Jul 20 2016
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14


Dive into the research topics of 'A wavelet-based encoding for neuroevolution'. Together they form a unique fingerprint.

Cite this