Automatic Evolution of Multimodal Behavior with Multi-Brain HyperNEAT

Jacob Schrum, Joel Lehman, Sebastian Risi

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


An important challenge in neuroevolution is to evolve multimodal behavior. Indirect network encodings can potentially answer this challenge. Yet in practice, indirect encodings do not yield effective multimodal controllers. This paper introduces novel multimodal extensions to HyperNEAT, a popular indirect encoding. A previous multimodal approach called situational policy geometry assumes that multiple brains benefit from being embedded within an explicit geometric space. However, this paper introduces HyperNEAT extensions for evolving many brains without assuming geometric relationships between them. The resulting Multi-Brain HyperNEAT can exploit human-specified task divisions, or can automatically discover when brains should be used, and how many to use. Experiments show that multi-brain approaches are more effective than HyperNEAT without multimodal extensions, and that brains without a geometric relation to each other are superior.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion
Number of pages2
Place of PublicationNew York, NY, USA
PublisherAssociation for Computing Machinery
Publication date2016
ISBN (Print)978-1-4503-4323-7
Publication statusPublished - 2016

Cite this