Reducing calibration effort for clonal selection based algorithms

A reinforcement learning approach

María Cristina Riff, Elizabeth Montero, Bertrand Neveu

Resultado de la investigación: Article

3 Citas (Scopus)

Resumen

In this paper we introduce (C, n)-strategy which improves the former C-strategy for on-line calibration of Clonal Selection based algorithms. In this approach, we are focused on a trade-off between the intensification and the diversification of the algorithm search. By using our approach, it allows us to reduce the number of the parameters of the algorithm respecting both the original design of the algorithm and its performance. The number of selected cells and the number of clones are dynamically controlled on-line, according to the algorithm's behavior. We report statistical comparisons using well-known clonalg based algorithms for solving combinatorial optimization problems. From the tests, we conclude that the tuning effort for Clonalg based algorithms is strongly reduced using our technique. Moreover, the dynamic control does not decrease the performance of the original version of the algorithm. On the contrary, it has shown to improve it.

Idioma originalEnglish
Páginas (desde-hasta)54-67
Número de páginas14
PublicaciónKnowledge-Based Systems
Volumen41
DOI
EstadoPublished - 1 mar 2013

Huella dactilar

Reinforcement learning
Calibration
Combinatorial optimization
Tuning

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Citar esto

@article{5fb5c6a06b284ad1aac9d7db6080b98a,
title = "Reducing calibration effort for clonal selection based algorithms: A reinforcement learning approach",
abstract = "In this paper we introduce (C, n)-strategy which improves the former C-strategy for on-line calibration of Clonal Selection based algorithms. In this approach, we are focused on a trade-off between the intensification and the diversification of the algorithm search. By using our approach, it allows us to reduce the number of the parameters of the algorithm respecting both the original design of the algorithm and its performance. The number of selected cells and the number of clones are dynamically controlled on-line, according to the algorithm's behavior. We report statistical comparisons using well-known clonalg based algorithms for solving combinatorial optimization problems. From the tests, we conclude that the tuning effort for Clonalg based algorithms is strongly reduced using our technique. Moreover, the dynamic control does not decrease the performance of the original version of the algorithm. On the contrary, it has shown to improve it.",
keywords = "Artificial immune algorithms, Metaheuristics, On-line calibration, Parameter control, Tuning",
author = "Riff, {Mar{\'i}a Cristina} and Elizabeth Montero and Bertrand Neveu",
year = "2013",
month = "3",
day = "1",
doi = "10.1016/j.knosys.2012.12.009",
language = "English",
volume = "41",
pages = "54--67",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

Reducing calibration effort for clonal selection based algorithms : A reinforcement learning approach. / Riff, María Cristina; Montero, Elizabeth; Neveu, Bertrand.

En: Knowledge-Based Systems, Vol. 41, 01.03.2013, p. 54-67.

Resultado de la investigación: Article

TY - JOUR

T1 - Reducing calibration effort for clonal selection based algorithms

T2 - A reinforcement learning approach

AU - Riff, María Cristina

AU - Montero, Elizabeth

AU - Neveu, Bertrand

PY - 2013/3/1

Y1 - 2013/3/1

N2 - In this paper we introduce (C, n)-strategy which improves the former C-strategy for on-line calibration of Clonal Selection based algorithms. In this approach, we are focused on a trade-off between the intensification and the diversification of the algorithm search. By using our approach, it allows us to reduce the number of the parameters of the algorithm respecting both the original design of the algorithm and its performance. The number of selected cells and the number of clones are dynamically controlled on-line, according to the algorithm's behavior. We report statistical comparisons using well-known clonalg based algorithms for solving combinatorial optimization problems. From the tests, we conclude that the tuning effort for Clonalg based algorithms is strongly reduced using our technique. Moreover, the dynamic control does not decrease the performance of the original version of the algorithm. On the contrary, it has shown to improve it.

AB - In this paper we introduce (C, n)-strategy which improves the former C-strategy for on-line calibration of Clonal Selection based algorithms. In this approach, we are focused on a trade-off between the intensification and the diversification of the algorithm search. By using our approach, it allows us to reduce the number of the parameters of the algorithm respecting both the original design of the algorithm and its performance. The number of selected cells and the number of clones are dynamically controlled on-line, according to the algorithm's behavior. We report statistical comparisons using well-known clonalg based algorithms for solving combinatorial optimization problems. From the tests, we conclude that the tuning effort for Clonalg based algorithms is strongly reduced using our technique. Moreover, the dynamic control does not decrease the performance of the original version of the algorithm. On the contrary, it has shown to improve it.

KW - Artificial immune algorithms

KW - Metaheuristics

KW - On-line calibration

KW - Parameter control

KW - Tuning

UR - http://www.scopus.com/inward/record.url?scp=84873736637&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2012.12.009

DO - 10.1016/j.knosys.2012.12.009

M3 - Article

VL - 41

SP - 54

EP - 67

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -