Automated selection of appropriate pheromone representations in ant colony optimization

James Montgomery, Marcus Randall, Tim Hendtlass

Research output: Contribution to journalArticleResearchpeer-review

11 Citations (Scopus)

Abstract

Ant colony optimization (ACO) is a constructive metaheuristic that uses an analogue of ant trail pheromones to learn about good features of solutions. Critically, the pheromone representation for a particular problem is usually chosen intuitively rather than by following any systematic process. In some representations, distinct solutions appear multiple times, increasing the effective size of the search space and potentially misleading ants as to the true learned value of those solutions. In this article, we present a novel system for automatically generating appropriate pheromone representations, based on the characteristics of the problem model that ensures unique pheromone representation of solutions. This is the first stage in the development of a generalized ACO system that could be applied to a wide range of problems with line or no modification. However, the system we propose may be used in the development of any problem-specific ACO algorithm.

Original languageEnglish
Pages (from-to)269-291
Number of pages23
JournalArtificial Life
Volume11
Issue number3
DOIs
Publication statusPublished - Jun 2005

Fingerprint

Ants
Ant colony optimization
Pheromones

Cite this

Montgomery, James ; Randall, Marcus ; Hendtlass, Tim. / Automated selection of appropriate pheromone representations in ant colony optimization. In: Artificial Life. 2005 ; Vol. 11, No. 3. pp. 269-291.
@article{4f54f7b5219a4fb39d7267ccb0bedbf7,
title = "Automated selection of appropriate pheromone representations in ant colony optimization",
abstract = "Ant colony optimization (ACO) is a constructive metaheuristic that uses an analogue of ant trail pheromones to learn about good features of solutions. Critically, the pheromone representation for a particular problem is usually chosen intuitively rather than by following any systematic process. In some representations, distinct solutions appear multiple times, increasing the effective size of the search space and potentially misleading ants as to the true learned value of those solutions. In this article, we present a novel system for automatically generating appropriate pheromone representations, based on the characteristics of the problem model that ensures unique pheromone representation of solutions. This is the first stage in the development of a generalized ACO system that could be applied to a wide range of problems with line or no modification. However, the system we propose may be used in the development of any problem-specific ACO algorithm.",
author = "James Montgomery and Marcus Randall and Tim Hendtlass",
year = "2005",
month = "6",
doi = "10.1162/1064546054407149",
language = "English",
volume = "11",
pages = "269--291",
journal = "Artificial Life",
issn = "1064-5462",
publisher = "MIT Press - Journals",
number = "3",

}

Automated selection of appropriate pheromone representations in ant colony optimization. / Montgomery, James; Randall, Marcus; Hendtlass, Tim.

In: Artificial Life, Vol. 11, No. 3, 06.2005, p. 269-291.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Automated selection of appropriate pheromone representations in ant colony optimization

AU - Montgomery, James

AU - Randall, Marcus

AU - Hendtlass, Tim

PY - 2005/6

Y1 - 2005/6

N2 - Ant colony optimization (ACO) is a constructive metaheuristic that uses an analogue of ant trail pheromones to learn about good features of solutions. Critically, the pheromone representation for a particular problem is usually chosen intuitively rather than by following any systematic process. In some representations, distinct solutions appear multiple times, increasing the effective size of the search space and potentially misleading ants as to the true learned value of those solutions. In this article, we present a novel system for automatically generating appropriate pheromone representations, based on the characteristics of the problem model that ensures unique pheromone representation of solutions. This is the first stage in the development of a generalized ACO system that could be applied to a wide range of problems with line or no modification. However, the system we propose may be used in the development of any problem-specific ACO algorithm.

AB - Ant colony optimization (ACO) is a constructive metaheuristic that uses an analogue of ant trail pheromones to learn about good features of solutions. Critically, the pheromone representation for a particular problem is usually chosen intuitively rather than by following any systematic process. In some representations, distinct solutions appear multiple times, increasing the effective size of the search space and potentially misleading ants as to the true learned value of those solutions. In this article, we present a novel system for automatically generating appropriate pheromone representations, based on the characteristics of the problem model that ensures unique pheromone representation of solutions. This is the first stage in the development of a generalized ACO system that could be applied to a wide range of problems with line or no modification. However, the system we propose may be used in the development of any problem-specific ACO algorithm.

UR - http://www.scopus.com/inward/record.url?scp=22944463619&partnerID=8YFLogxK

U2 - 10.1162/1064546054407149

DO - 10.1162/1064546054407149

M3 - Article

VL - 11

SP - 269

EP - 291

JO - Artificial Life

JF - Artificial Life

SN - 1064-5462

IS - 3

ER -