Automatic Evolution of Multimodal Behavior with Multi-Brain HyperNEAT

This is an Accepted Manuscript of an article published in Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion (pp. 21–22). New York, NY, USA: ACM. https://doi.org/10.1145/2908961.2908965

Schrum, Jacob

Lehman, Joel

Risi, Sebastian

2016-12-08

2016-12-08

2016

Schrum, J., Lehman, J., & Risi, S. (2016). Automatic Evolution of Multimodal Behavior with Multi-Brain HyperNEAT. In Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion (pp. 21–22). New York, NY, USA: ACM. https://doi.org/10.1145/2908961.2908965

https://collections.southwestern.edu/s/suscholar/item/223

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.

English

ACM

Multimodal Behavior

HyperNEAT

Multi-Brain HyperNEAT

Indirect Encoding

Article