文献类型：期刊文献

英文题名：Learning to Guide Particle Search for Dynamic Multiobjective Optimization

作者：Song, Wei[1];Liu, Shaocong[1];Wang, Xinjie[2];Guo, Yinan[3];Yang, Shengxiang[4];Jin, Yaochu[5]

机构：[1]Jiangnan Univ, Sch Artificial Intelligence & Comp Sci, Jiangsu Prov Engn Lab Pattern Recognit & Computat, Wuxi 214122, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[3]China Univ Min & Technol, Sch Informat & Control Engn, Xuzhou 221116, Peoples R China;[4]De Montfort Univ, Inst Artificial Intelligence, Sch Comp Sci & Informat, Leicester LE1 9BH, England;[5]Westlake Univ, Sch Engn, Trustworth & Gen Artificial Intelligence Lab, Hangzhou 331712, Peoples R China

年份：2024

卷号：54

期号：9

起止页码：5529

外文期刊名：IEEE TRANSACTIONS ON CYBERNETICS

收录：;EI(收录号：20240915652068);WOS:【SCI-EXPANDED(收录号:WOS:001176573200001)】；

基金：No Statement Available

语种：英文

外文关键词：Heuristic algorithms; Statistics; Sociology; Optimization; Prediction algorithms; Optical fibers; Costs; Dynamic multiobjective optimization; incremental learning; neural network; particle swarm optimization; reinforcement learning

摘要：Dynamic multiobjective optimization problems (DMOPs) are characterized by multiple objectives that change over time in varying environments. More specifically, environmental changes can be described as various dynamics. However, it is difficult for existing dynamic multiobjective algorithms (DMOAs) to handle DMOPs due to their inability to learn in different environments to guide the search. Besides, solving DMOPs is typically an online task, requiring low computational cost of a DMOA. To address the above challenges, we propose a particle search guidance network (PSGN), capable of directing individuals' search actions, including learning target selection and acceleration coefficient control. PSGN can learn the actions that should be taken in each environment through rewarding or punishing the network by reinforcement learning. Thus, PSGN is capable of tackling DMOPs of various dynamics. Additionally, we efficiently adjust PSGN hidden nodes and update the output weights in an incremental learning way, enabling PSGN to direct particle search at a low computational cost. We compare the proposed PSGN with seven state-of-the-art algorithms, and the excellent performance of PSGN verifies that it can handle DMOPs of various dynamics in a computationally very efficient way.