Data-efficient Neuroevolution with Kernel-Based Surrogate Models

  • Surrogate-assistance approaches have long been used in computationally expensive domains to improve the data-efficiency of optimization algorithms. Neuroevolution, however, has so far resisted the application of these techniques because it requires the surrogate model to make fitness predictions based on variable topologies, instead of a vector of parameters. Our main insight is that we can sidestep this problem by using kernel-based surrogate models, which require only the definition of a distance measure between individuals. Our second insight is that the well-established Neuroevolution of Augmenting Topologies (NEAT) algorithm provides a computationally efficient distance measure between dissimilar networks in the form of "compatibility distance", initially designed to maintain topological diversity. Combining these two ideas, we introduce a surrogate-assisted neuroevolution algorithm that combines NEAT and a surrogate model built using a compatibility distance kernel. We demonstrate the data-efficiency of this new algorithm on the low dimensional cart-pole swing-up problem, as well as the higher dimensional half-cheetah running task. In both tasks the surrogate-assisted variant achieves the same or better results with several times fewer function evaluations as the original NEAT.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar Availability
Metadaten
Document Type:Preprint
Language:English
Parent Title (English):GECCO ’18: Genetic and Evolutionary Computation Conference, July 15–19, 2018, Kyoto, Japan
Pagenumber:8
DOI:10.1145/3205455.3205510
Publisher:arXiv.org
Publication year:2018
Tag:NEAT; Neuroevolution; Surrogate Modeling
Departments, institutes and facilities:Fachbereich Informatik
Dewey Decimal Classification (DDC):000 Informatik, Informationswissenschaft, allgemeine Werke / 000 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Entry in this database:2018/05/04

$Rev: 12793 $