A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation

Diego Tapia; BRODERICK CRAWFORD LABRIN; RICARDO JAVIER SOTO DE GIORGIS; Felipe Cisternas-Caneo; José Lemus-Romani; Mauricio Castillo; José García; WENCESLAO ENRIQUE PALMA MUÑOZ; Fernando Paredes; Sanjay Misra

doi:10.1007/978-3-030-61702-8_2

A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation

Diego Tapia, BRODERICK CRAWFORD LABRIN, RICARDO JAVIER SOTO DE GIORGIS, Felipe Cisternas-Caneo, José Lemus-Romani, Mauricio Castillo, José García, WENCESLAO ENRIQUE PALMA MUÑOZ, Fernando Paredes, Sanjay Misra

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Many Metaheuristics solve optimization problems in the continuous domain, so it is necessary to apply binarization schemes to solve binary problems, this selection that is not trivial since it impacts the heart of the search strategy: its ability to explore. This paper proposes a Hyperheuristic Binarization Framework based on a Machine Learning technique of Reinforcement Learning to select the appropriate binarization strategy, which is applied in a Low Level Metaheuristic. The proposed implementation is composed of a High Level Metaheuristic, Ant Colony Optimization, using Q-Learning replacing the pheromone trace component. In the Low Level Metaheuristic, we use a Grey Wolf Optimizer to solve the binary problem with binarization scheme fixed by ants. This framework allowing a better balance between exploration and exploitation, and can be applied selecting others low level components.

Original language	English
Title of host publication	Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings
Editors	Hector Florez, Sanjay Misra
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	14-28
Number of pages	15
ISBN (Print)	9783030617011
DOIs	https://doi.org/10.1007/978-3-030-61702-8_2
State	Published - 2020
Externally published	Yes
Event	3rd International Conference on Applied Informatics, ICAI 2020 - Ota, Nigeria Duration: 29 Oct 2020 → 31 Oct 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1277 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	3rd International Conference on Applied Informatics, ICAI 2020
Country/Territory	Nigeria
City	Ota
Period	29/10/20 → 31/10/20

Keywords

Binarization framework
Combinatorial optimization
Hyperheuristics
Metaheuristics
Reinforcement learning

Access to Document

10.1007/978-3-030-61702-8_2

Cite this

Tapia, D., CRAWFORD LABRIN, BRODERICK., SOTO DE GIORGIS, RICARDO. JAVIER., Cisternas-Caneo, F., Lemus-Romani, J., Castillo, M., García, J., PALMA MUÑOZ, WENCESLAO. ENRIQUE., Paredes, F., & Misra, S. (2020). A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation. In H. Florez, & S. Misra (Eds.), Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings (pp. 14-28). (Communications in Computer and Information Science; Vol. 1277 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-61702-8_2

Tapia, Diego ; CRAWFORD LABRIN, BRODERICK ; SOTO DE GIORGIS, RICARDO JAVIER et al. / A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation. Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings. editor / Hector Florez ; Sanjay Misra. Springer Science and Business Media Deutschland GmbH, 2020. pp. 14-28 (Communications in Computer and Information Science).

@inproceedings{945d56c593754502bc7b2f738db65a3c,

title = "A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation",

abstract = "Many Metaheuristics solve optimization problems in the continuous domain, so it is necessary to apply binarization schemes to solve binary problems, this selection that is not trivial since it impacts the heart of the search strategy: its ability to explore. This paper proposes a Hyperheuristic Binarization Framework based on a Machine Learning technique of Reinforcement Learning to select the appropriate binarization strategy, which is applied in a Low Level Metaheuristic. The proposed implementation is composed of a High Level Metaheuristic, Ant Colony Optimization, using Q-Learning replacing the pheromone trace component. In the Low Level Metaheuristic, we use a Grey Wolf Optimizer to solve the binary problem with binarization scheme fixed by ants. This framework allowing a better balance between exploration and exploitation, and can be applied selecting others low level components.",

keywords = "Binarization framework, Combinatorial optimization, Hyperheuristics, Metaheuristics, Reinforcement learning",

author = "Diego Tapia and {CRAWFORD LABRIN}, BRODERICK and {SOTO DE GIORGIS}, {RICARDO JAVIER} and Felipe Cisternas-Caneo and Jos{\'e} Lemus-Romani and Mauricio Castillo and Jos{\'e} Garc{\'i}a and {PALMA MU{\~N}OZ}, {WENCESLAO ENRIQUE} and Fernando Paredes and Sanjay Misra",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; null ; Conference date: 29-10-2020 Through 31-10-2020",

year = "2020",

doi = "10.1007/978-3-030-61702-8_2",

language = "English",

isbn = "9783030617011",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "14--28",

editor = "Hector Florez and Sanjay Misra",

booktitle = "Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings",

}

Tapia, D, CRAWFORD LABRIN, BRODERICK , SOTO DE GIORGIS, RICARDOJAVIER, Cisternas-Caneo, F, Lemus-Romani, J, Castillo, M, García, J , PALMA MUÑOZ, WENCESLAOENRIQUE, Paredes, F & Misra, S 2020, A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation. in H Florez & S Misra (eds), Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings. Communications in Computer and Information Science, vol. 1277 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 14-28, 3rd International Conference on Applied Informatics, ICAI 2020, Ota, Nigeria, 29/10/20. https://doi.org/10.1007/978-3-030-61702-8_2

A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation. / Tapia, Diego; CRAWFORD LABRIN, BRODERICK ; SOTO DE GIORGIS, RICARDO JAVIER et al.

Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings. ed. / Hector Florez; Sanjay Misra. Springer Science and Business Media Deutschland GmbH, 2020. p. 14-28 (Communications in Computer and Information Science; Vol. 1277 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation

AU - Tapia, Diego

AU - CRAWFORD LABRIN, BRODERICK

AU - SOTO DE GIORGIS, RICARDO JAVIER

AU - Cisternas-Caneo, Felipe

AU - Lemus-Romani, José

AU - Castillo, Mauricio

AU - García, José

AU - PALMA MUÑOZ, WENCESLAO ENRIQUE

AU - Paredes, Fernando

AU - Misra, Sanjay

PY - 2020

Y1 - 2020

N2 - Many Metaheuristics solve optimization problems in the continuous domain, so it is necessary to apply binarization schemes to solve binary problems, this selection that is not trivial since it impacts the heart of the search strategy: its ability to explore. This paper proposes a Hyperheuristic Binarization Framework based on a Machine Learning technique of Reinforcement Learning to select the appropriate binarization strategy, which is applied in a Low Level Metaheuristic. The proposed implementation is composed of a High Level Metaheuristic, Ant Colony Optimization, using Q-Learning replacing the pheromone trace component. In the Low Level Metaheuristic, we use a Grey Wolf Optimizer to solve the binary problem with binarization scheme fixed by ants. This framework allowing a better balance between exploration and exploitation, and can be applied selecting others low level components.

AB - Many Metaheuristics solve optimization problems in the continuous domain, so it is necessary to apply binarization schemes to solve binary problems, this selection that is not trivial since it impacts the heart of the search strategy: its ability to explore. This paper proposes a Hyperheuristic Binarization Framework based on a Machine Learning technique of Reinforcement Learning to select the appropriate binarization strategy, which is applied in a Low Level Metaheuristic. The proposed implementation is composed of a High Level Metaheuristic, Ant Colony Optimization, using Q-Learning replacing the pheromone trace component. In the Low Level Metaheuristic, we use a Grey Wolf Optimizer to solve the binary problem with binarization scheme fixed by ants. This framework allowing a better balance between exploration and exploitation, and can be applied selecting others low level components.

KW - Binarization framework

KW - Combinatorial optimization

KW - Hyperheuristics

KW - Metaheuristics

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85096411243&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-61702-8_2

DO - 10.1007/978-3-030-61702-8_2

M3 - Conference contribution

AN - SCOPUS:85096411243

SN - 9783030617011

T3 - Communications in Computer and Information Science

SP - 14

EP - 28

BT - Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings

A2 - Florez, Hector

A2 - Misra, Sanjay

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 29 October 2020 through 31 October 2020

ER -

Tapia D, CRAWFORD LABRIN BRODERICK , SOTO DE GIORGIS RICARDOJAVIER, Cisternas-Caneo F, Lemus-Romani J, Castillo M et al. A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation. In Florez H, Misra S, editors, Applied Informatics - 3rd International Conference, ICAI 2020, Proceedings. Springer Science and Business Media Deutschland GmbH. 2020. p. 14-28. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-61702-8_2

A Q-Learning Hyperheuristic Binarization Framework to Balance Exploration and Exploitation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this