QQLMPA : A quasi-opposition learning and Q-learning based marine predators algorithm
Journal article
Zhao, Shangrui, Wu, Yulu, Tan, Shuang, Wu, Jinran, Cui, Zhesen and Wang, You-Gan. (2023). QQLMPA : A quasi-opposition learning and Q-learning based marine predators algorithm. Expert Systems with Applications. 213(Part C), p. Article 119246. https://doi.org/10.1016/j.eswa.2022.119246
Authors | Zhao, Shangrui, Wu, Yulu, Tan, Shuang, Wu, Jinran, Cui, Zhesen and Wang, You-Gan |
---|---|
Abstract | Many engineering and scientific problems in the real-world boil down to optimization problems, which are difficult to solve by using traditional methods. Meta-heuristics are appealing algorithms for solving optimization problems while keeping computational costs reasonable. The marine predators algorithm (MPA) is a modern optimization meta-heuristic, inspired by widespread Lévy and Brownian foraging strategies in ocean predators as well as optimal encounter rate strategies in biological interactions between predator and prey. However, MPA is not without its shortcomings. In this paper, a quasi-opposition based learning and Q-learning based marine predators algorithm (QQLMPA) is proposed. This offers multiple improvements over standard MPA. Primely, Q-learning allows MPA to fully use the information generated by previous iterations. And also, quasi-opposition based learning serves to increase population diversity, reducing the risk of convergence to inferior local optima. Numerical experiments demonstrate better performance by QQLMPA on 32 benchmark optimization functions and three engineering problems: designs of pressure vessel, hydro-static thrust bearing, and speed reducer. |
Keywords | Q-learning algorithm; marine predators algorithm; meta-heuristics; quasi-opposition based learning |
Year | 2023 |
Journal | Expert Systems with Applications |
Journal citation | 213 (Part C), p. Article 119246 |
Publisher | Elsevier Ltd |
ISSN | 0957-4174 |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.eswa.2022.119246 |
Scopus EID | 2-s2.0-85142200037 |
Page range | 1-19 |
Funder | Australian Research Council (ARC) |
Chinese Fundamental Research Funds for the Central Universities | |
Publisher's version | License All rights reserved File Access Level Controlled |
Output status | Published |
Publication dates | |
Online | 12 Nov 2022 |
Publication process dates | |
Accepted | 06 Nov 2022 |
Deposited | 19 Jul 2023 |
Grant ID | DP160104292 |
WUT: 213114009 |
https://acuresearchbank.acu.edu.au/item/8z553/qqlmpa-a-quasi-opposition-learning-and-q-learning-based-marine-predators-algorithm
Restricted files
Publisher's version
185
total views0
total downloads7
views this month0
downloads this month