A fitness landscape ruggedness multiobjective differential evolution algorithm with a reinforcement learning strategy

被引:42
作者
Huang, Ying [1 ]
Li, Wei [2 ]
Tian, Furong [2 ]
Meng, Xiang [2 ]
机构
[1] Gannan Normal Univ, Inst Math & Comp Sci, Ganzhou, Peoples R China
[2] Jiangxi Univ Sci & Technol, Sch Informat Engn, Ganzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
Multiobjective; Differential evolution; Reinforcement learning; Fitness landscape; Search strategy; OPTIMIZATION; NEUTRALITY;
D O I
10.1016/j.asoc.2020.106693
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Optimization is the process of finding and comparing feasible solutions and adopting the best one until no better solution can be found. Because solving real-world problems often involves simulations and multiobjective optimization, the results and solutions of these problems are conceptually different from those of single-objective problems. In single-objective optimization problems, the global optimal solution is the solution that yields the optimal value of the objective function. However, for multiobjective optimization problems, the optimal solutions are Pareto-optimal solutions produced by balancing multiple objective functions. The strategic variables calculated in multiobjective problems produce different effects on the mapping imbalance and the search redundancy in the search space. Therefore, this paper proposes a fitness landscape ruggedness multiobjective differential evolution (LRMODE) algorithm with a reinforcement learning strategy. The proposed algorithm analyses the ruggedness of landscapes using information entropy to estimate whether the local landscape has a unimodal or multimodal topology and then combines the outcome with a reinforcement learning strategy to determine the optimal probability distribution of the algorithm's search strategy set. The experimental results show that this novel algorithm can ameliorate the problem of search redundancy and search-space mapping imbalances, effectively improving the convergence of the search algorithm during the optimization process. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页数:13
相关论文
共 57 条
[41]   THE LANDSCAPE OF THE TRAVELING SALESMAN PROBLEM [J].
STADLER, PF ;
SCHNABL, W .
PHYSICS LETTERS A, 1992, 161 (04) :337-344
[42]  
Sutton R. S., 1998, ASIA PACIFIC C SIMUL, P195
[43]   Adaptive heuristic search algorithm for discrete variables based multi-objective optimization [J].
Tang, Long ;
Wang, Hu ;
Li, Guangyao ;
Xu, Fengxiang .
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2013, 48 (04) :821-836
[44]   Multidimensional knapsack problem: A fitness landscape analysis [J].
Tavares, Jorge ;
Pereira, Francisco B. ;
Costa, Ernesto .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2008, 38 (03) :604-616
[45]   A hybrid convolution network for serial number recognition on banknotes [J].
Wang, Feng ;
Zhu, Huiqing ;
Li, Wei ;
Li, Kangshun .
INFORMATION SCIENCES, 2020, 512 :952-963
[46]   An adaptive weight vector guided evolutionary algorithm for preference-based multi-objective optimization [J].
Wang, Feng ;
Li, Yixuan ;
Zhang, Heng ;
Hu, Ting ;
Shen, Xiao-Liang .
SWARM AND EVOLUTIONARY COMPUTATION, 2019, 49 :220-233
[47]   External archive matching strategy for MOEA/D [J].
Wang, Feng ;
Zhang, Heng ;
Li, Yixuan ;
Zhao, Yaoyu ;
Rao, Qi .
SOFT COMPUTING, 2018, 22 (23) :7833-7846
[48]   A hybrid particle swarm optimization algorithm using adaptive learning strategy [J].
Wang, Feng ;
Zhang, Heng ;
Li, Kangshun ;
Lin, Zhiyi ;
Yang, Jun ;
Shen, Xiao-Liang .
INFORMATION SCIENCES, 2018, 436 :162-177
[49]  
Wang Feng, 2019, IEEE T EVOL COMPUT
[50]  
WRIGHT SEWALL, 1932, PROC SIXTH INTERNAT CONGR GENETICS ITHACA NEW YORK, V1, P356