Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning
International Journal of Intelligent Systems · 03.01.2024 · 2024 · 1-17
DOI: 10.1155/2024/6740701 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Intelligent Systems, erschienen am 03.01.2024. Verfasst von Tianwei Zhou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Ministry of Education of the People’s Republic of China, Guangdong Provincial Philosophy and Social Sciences Planning Project.
Abstract (Originalsprache)
To address the challenge of parameter adjustment in complex environments, this paper introduces a transfer learning-based parameter control framework via deep reinforcement learning for multiobjective evolutionary algorithms (MOEAs). To avoid the requirement for accurate Pareto front information, this framework is proposed with comprehensive global-state information, including basic problem features, the relative position of individuals, the distribution of fitness value, and the grid-IGD. Building on this framework, four reinforced multiobjective evolutionary algorithms (r-MOEAs) are proposed and tested on four DTLZ benchmarks and eight WFG benchmarks. The results of the comparative analyses reveal that compared with the original MOEAs, the four r-MOEAs exhibit faster convergence and stronger robustness. It is also confirmed that our proposed parameter control framework has the capability to learn knowledge from different experiences and improve the performance of MOEAs.
Förderung
- National Natural Science Foundation of China
- Ministry of Education of the People’s Republic of China
- Guangdong Provincial Philosophy and Social Sciences Planning Project
- Basic and Applied Basic Research Foundation of Guangdong Province
- Guangdong Province Innovation Team Intelligent Management and Interdisciplinary Innovation
- Special Projects in Key Fields of Ordinary Colleges and Universities in Guangdong Province
Zitieren
APA
Zhou, T., Zhang, W., Niu, B., He, P., & Yue, G. (2024). Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning. International Journal of Intelligent Systems, 2024, 1-17. https://doi.org/10.1155/2024/6740701
Vancouver
Zhou T, Zhang W, Niu B, He P, Yue G. Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning. International Journal of Intelligent Systems. 2024;2024:1-17. doi:10.1155/2024/6740701
BibTeX
@article{Zhou2024,
author = {Zhou, Tianwei and Zhang, Wenwen and Niu, Ben and He, Pengcheng and Yue, Guanghui},
title = {Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning},
journal = {International Journal of Intelligent Systems},
year = {2024},
volume = {2024},
pages = {1--17},
doi = {10.1155/2024/6740701}
}
EUVIMED