On-the-fly calibrating strategies for evolutionary algorithms

Elizabeth Montero, María Cristina Riff

Resultado de la investigación: Article

19 Citas (Scopus)

Resumen

The issue of controlling values of various parameters of an evolutionary algorithm is one of the most important and interesting areas of research in evolutionary computation. In this paper we propose two new parameter control strategies for evolutionary algorithms based on the ideas of reinforcement learning. These strategies provide efficient and low-cost adaptive techniques for parameter control and they preserve the original design of the evolutionary algorithm, as they can be included without changing either the structure of the algorithm nor its operators design.

Idioma originalEnglish
Páginas (desde-hasta)552-566
Número de páginas15
PublicaciónInformation Sciences
Volumen181
N.º3
DOI
EstadoPublished - 1 feb 2011

Huella dactilar

Evolutionary algorithms
Evolutionary Algorithms
Adaptive Techniques
Evolutionary Computation
Reinforcement Learning
Control Parameter
Control Strategy
Reinforcement learning
Mathematical operators
Operator
Strategy
Costs
Design
Control strategy
Evolutionary computation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Software
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Citar esto

Montero, Elizabeth ; Riff, María Cristina. / On-the-fly calibrating strategies for evolutionary algorithms. En: Information Sciences. 2011 ; Vol. 181, N.º 3. pp. 552-566.
@article{4ea53a136d93478eb877896f44dd608c,
title = "On-the-fly calibrating strategies for evolutionary algorithms",
abstract = "The issue of controlling values of various parameters of an evolutionary algorithm is one of the most important and interesting areas of research in evolutionary computation. In this paper we propose two new parameter control strategies for evolutionary algorithms based on the ideas of reinforcement learning. These strategies provide efficient and low-cost adaptive techniques for parameter control and they preserve the original design of the evolutionary algorithm, as they can be included without changing either the structure of the algorithm nor its operators design.",
keywords = "Evolutionary algorithms, Parameter control",
author = "Elizabeth Montero and Riff, {Mar{\'i}a Cristina}",
year = "2011",
month = "2",
day = "1",
doi = "10.1016/j.ins.2010.09.016",
language = "English",
volume = "181",
pages = "552--566",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "3",

}

On-the-fly calibrating strategies for evolutionary algorithms. / Montero, Elizabeth; Riff, María Cristina.

En: Information Sciences, Vol. 181, N.º 3, 01.02.2011, p. 552-566.

Resultado de la investigación: Article

TY - JOUR

T1 - On-the-fly calibrating strategies for evolutionary algorithms

AU - Montero, Elizabeth

AU - Riff, María Cristina

PY - 2011/2/1

Y1 - 2011/2/1

N2 - The issue of controlling values of various parameters of an evolutionary algorithm is one of the most important and interesting areas of research in evolutionary computation. In this paper we propose two new parameter control strategies for evolutionary algorithms based on the ideas of reinforcement learning. These strategies provide efficient and low-cost adaptive techniques for parameter control and they preserve the original design of the evolutionary algorithm, as they can be included without changing either the structure of the algorithm nor its operators design.

AB - The issue of controlling values of various parameters of an evolutionary algorithm is one of the most important and interesting areas of research in evolutionary computation. In this paper we propose two new parameter control strategies for evolutionary algorithms based on the ideas of reinforcement learning. These strategies provide efficient and low-cost adaptive techniques for parameter control and they preserve the original design of the evolutionary algorithm, as they can be included without changing either the structure of the algorithm nor its operators design.

KW - Evolutionary algorithms

KW - Parameter control

UR - http://www.scopus.com/inward/record.url?scp=78449297174&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2010.09.016

DO - 10.1016/j.ins.2010.09.016

M3 - Article

VL - 181

SP - 552

EP - 566

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 3

ER -