Advancements in Q-learning meta-heuristic optimization algorithms: A survey

被引：7
作者：
Yang, Yang [1 ,2 ]
Gao, Yuchao [1 ,2 ]
Ding, Zhe [3 ]
Wu, Jinran [4 ]
Zhang, Shaotong [5 ]
Han, Feifei [4 ]
Qiu, Xuelan [4 ]
Gao, Shangce [6 ]
Wang, You-Gan [7 ]
机构：
[1] Nanjing Univ Posts & Telecommun, Coll Automat, Nanjing, Peoples R China
[2] Nanjing Univ Posts & Telecommun, Coll Artificial Intelligence, Nanjing, Peoples R China
[3] Queensland Univ Technol, Sch Comp Sci, Brisbane, Qld, Australia
[4] Australian Catholic Univ, Fac Educ & Arts, Banyo, Qld, Australia
[5] Ocean Univ China, Coll Marine Geosci, Frontiers Sci Ctr Deep Ocean Multispheres & Earth, Key Lab Submarine Geosci & Prospecting Tech,MOE, Qingdao, Peoples R China
[6] Univ Toyama, Fac Engn, Toyama, Japan
[7] Univ Queensland, Sch Math & Phys, St Lucia, Qld, Australia
来源：
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY | 2024年 / 14卷 / 06期
关键词：
meta-heuristic; optimization; Q-learning; reinforcement learning; PARTICLE SWARM OPTIMIZATION; AUTOMATIC-GENERATION CONTROL; DIFFERENTIAL EVOLUTION; REINFORCEMENT; GRASP;
D O I：
10.1002/widm.1548
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper reviews the integration of Q-learning with meta-heuristic algorithms (QLMA) over the last 20 years, highlighting its success in solving complex optimization problems. We focus on key aspects of QLMA, including parameter adaptation, operator selection, and balancing global exploration with local exploitation. QLMA has become a leading solution in industries like energy, power systems, and engineering, addressing a range of mathematical challenges. Looking forward, we suggest further exploration of meta-heuristic integration, transfer learning strategies, and techniques to reduce state space. This article is categorized under: Technologies > Computational Intelligence Technologies > Artificial Intelligence
引用
收藏
页数：37
相关论文
共 188 条
[21]   Algorithm for overcoming the curse of dimensionality for state-dependent Hamilton-Jacobi equations [J].
Chow, Yat Tin ;
Darbon, Jerome ;
Osher, Stanley ;
Yin, Wotao .
JOURNAL OF COMPUTATIONAL PHYSICS, 2019, 387 :376-409
[22]   Q-Learning: Theory and Applications [J].
Clifton, Jesse ;
Laber, Eric .
ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, VOL 7, 2020, 2020, 7 :279-301
[23]  
[崔建双 Cui Jianshuang], 2022, [计算机集成制造系统, Computer Integrated Manufacturing Systems], V28, P1472
[24]   Combining trajectory optimization, supervised machine learning, and model structure for mitigating the curse of dimensionality in the control of bipedal robots [J].
Da, Xingye ;
Grizzle, Jessy .
INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2019, 38 (09) :1063-1097
[25]   Intelligent-based multi-robot path planning inspired by improved classical Q-learning and improved particle swarm optimization with perturbed velocity [J].
Das, P. K. ;
Behera, H. S. ;
Panigrahi, B. K. .
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH, 2016, 19 (01) :651-669
[26]   Proposal for improvement of GRASP metaheuristic and Genetic Algorithm using the Q-Learning Algorithm [J].
de Lima, Francisco Chagas, Jr. ;
de Melo, Jorge D. ;
Neto, Adriao Duarte D. .
PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND APPLICATIONS, 2007, :465-+
[27]  
Junior FCD, 2007, IEEE IJCNN, P1243
[28]   Using the Q-learning Algorithm in the Constructive Phase of the GRASP and Reactive GRASP Metaheuristics [J].
de Lima Junior, Francisco Chagas ;
de Melo, Jorge Dantas ;
Doria Neto, Adriao Duarte .
2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, :4169-+
[29]  
Dejun Cai, 2019, 2019 IEEE 5th International Conference on Computer and Communications (ICCC), P1881, DOI 10.1109/ICCC47050.2019.9064104
[30]   An improved differential evolution algorithm and its application in optimization problem [J].
Deng, Wu ;
Shang, Shifan ;
Cai, Xing ;
Zhao, Huimin ;
Song, Yingjie ;
Xu, Junjie .
SOFT COMPUTING, 2021, 25 (07) :5277-5298
12345678910