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.
Document Type: | Conference Object |
---|---|
Language: | English |
Author: | Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret |
Parent Title (English): | GECCO ’18: Genetic and Evolutionary Computation Conference, July 15–19, 2018, Kyoto, Japan |
First Page: | 85 |
Last Page: | 92 |
ISBN: | 978-1-4503-5618-3 |
DOI: | https://doi.org/10.1145/3205455.3205510 |
ArXiv Id: | http://arxiv.org/abs/1804.05364 |
Publisher: | ACM |
Place of publication: | New York, NY, USA |
Date of first publication: | 2018/07/02 |
Award: | Best Paper Award |
Funding: | This work received funding from the European Research Council under the European Union’s Horizon 2020 research and innovation programme (grant agreement number 637972, project "ResiB bots") and the German Federal Ministry of Education and Research under the Forschung an Fachhochschulen mit Unternehmen programme (grant agreement number 03FH012PX5 project "Aeromat"). |
Keyword: | NEAT; Neuroevolution; Surrogate Modeling |
Departments, institutes and facilities: | Fachbereich Informatik |
Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) | |
Projects: | AErOMAt - Automatisiertes Entwickeln aerodynamischer Strukturen und Fahrzeuge mithilfe evolutionärer Optimierung und Surrogatmodellierung (DE/BMBF/03FH012PX5,13FH012PX5) |
Dewey Decimal Classification (DDC): | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik |
Entry in this database: | 2018/05/04 |