Learning to Adapt Genetic Algorithms for Multi-Objective Flexible Job Shop Scheduling Problems

被引：2

作者：

Reijnen, Robbert ^{[1
]}

Bukhsh, Zaharah ^{[1
]}

Zhang, Yingqian ^{[1
]}

Guzek, Mateusz ^{[2
]}

机构：

[1] Eindhoven Univ Technol, Dept Ind Engn, Eindhoven, Netherlands

[2] Goodyear Innovat Ctr Luxembourg, Decis Sci & Optimizat, Colmar Berg, Luxembourg

来源：

PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION | 2023年

关键词：

Evolutionary Algorithms; Deep Reinforcement Learning; Adaptive Parameter Control; Flexible Job Shop Scheduling; OPTIMIZATION;

D O I：

10.1145/3583133.3590700

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The configuration of Evolutionary Algorithm (EA) parameters is a significant challenge. While previous studies have examined methods for configuring EA parameters, there remains a lack of a general solution for optimizing these parameters. To overcome this, we propose DEMOCA, an automated Deep Reinforcement Learning (DRL) method for online control of multi-objective EA parameters. When tested on a multi-objective Flexible Job Shop Scheduling Problem (FJSP) using a Genetic Algorithm (GA), DEMOCA was found to be as effective as grid search while requiring significantly less training cost.

引用

页码：315 / 318

页数：4

共 13 条

[1] A Systematic Literature Review of Adaptive Parameter Control Methods for Evolutionary Algorithms [J].

Aleti, Aldeida ;

Moser, Irene .

ACM COMPUTING SURVEYS, 2016, 49 (03)

[2]

Brandimarte P., 1993, Annals of Operations Research, V41, P157, DOI 10.1007/BF02023073

[3]

Coello C.C., 2007, EVOLUTIONARY ALGORIT, DOI [10.1007/978-0-387-36797-2, DOI 10.1007/978-0-387-36797-2]

[4] Three new metrics to measure the convergence of metaheuristics towards the Pareto frontier and the aesthetic of a set of solutions in biobjective optimization [J].

Collette, Y ;

Siarry, P .

COMPUTERS & OPERATIONS RESEARCH, 2005, 32 (04) :773-792

[5] A fast and elitist multiobjective genetic algorithm: NSGA-II [J].

Deb, K ;

Pratap, A ;

Agarwal, S ;

Meyarivan, T .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (02) :182-197

[6] Mathematical modeling and heuristic approaches to flexible job shop scheduling problems [J].

Fattahi, Parviz ;

Mehrabad, Mohammad Saidi ;

Jolai, Fariborz .

JOURNAL OF INTELLIGENT MANUFACTURING, 2007, 18 (03) :331-342

[7] Approach by localization and multiobjective evolutionary optimization for flexible job-shop scheduling problems [J].

Kacem, I ;

Hammadi, S ;

Borne, P .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2002, 32 (01) :1-13

[8] Parameter Control in Evolutionary Algorithms: Trends and Challenges [J].

Karafotias, Giorgos ;

Hoogendoorn, Mark ;

Eiben, A. E. .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2015, 19 (02) :167-187

[9] Deep Reinforcement Learning for Adaptive Parameter Control in Differential Evolution for Multi-Objective Optimization [J].

Reijnen, Robbert ;

Zhang, Yingqian ;

Bukhsh, Zaharah ;

Guzek, Mateusz .

2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2022, :804-811

[10]

Schulman J, 2017, Arxiv, DOI [arXiv:1707.06347, DOI 10.48550/ARXIV.1707.06347]

← 1 2 →