Hybrid Dynamic Resampling for Guided Evolutionary Multi-Objective Optimization
2015 (English)In: Evolutionary Multi-Criterion Optimization: 8th International Conference, EMO 2015, Guimarães, Portugal, March 29 --April 1, 2015. Proceedings, Part I / [ed] António Gaspar-Cunha, Carlos Henggeler Antunes, Carlos Coello Coello, Springer, 2015, 366-380 p.Conference paper (Refereed)
In Guided Evolutionary Multi-objective Optimization the goal is to find a diverse, but locally focused non-dominated front in a decision maker’s area of interest, as close as possible to the true Pareto-front. The optimization can focus its efforts towards the preferred area and achieve a better result [9, 17, 7, 13]. The modeled and simulated systems are often stochastic and a common method to handle the objective noise is Resampling. The given preference information allows to define better resampling strategies which further improve the optimization result. In this paper, resampling strategies are proposed that base the sampling allocation on multiple factors, and thereby combine multiple resampling strategies proposed by the authors in . These factors are, for example, the Pareto-rank of a solution and its distance to the decision maker’s area of interest. The proposed hybrid Dynamic Resampling Strategy DR2 is evaluated on the Reference point-guided NSGA-II optimization algorithm (R-NSGA-II) .
Place, publisher, year, edition, pages
Springer, 2015. 366-380 p.
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9018
evolutionary multi-objective optimization, guided search, reference point, dynamic resampling, budget allocation
Computer and Information Science Robotics
Research subject Natural sciences; Technology
IdentifiersURN: urn:nbn:se:his:diva-10814DOI: 10.1007/978-3-319-15934-8_25ISI: 000361702100025ScopusID: 2-s2.0-84925337390ISBN: 978-3-319-15934-8ISBN: 978-3-319-15933-1OAI: oai:DiVA.org:his-10814DiVA: diva2:799272
8th International Conference on Evolutionary Multi-Criterion Optimization, March 2015, Guimarães, Portugal