Particle swarm optimization integrating reinforcement learning and an adaptive regeneration mechanism
AIP Advances · 01.07.2026 · 16 (7)
DOI: 10.1063/5.0343006 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIP Advances, online erschienen am 15.07.2026. Verfasst von Han Tian und 2 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Province Colleges and Universities “Qinglan Project”, Huai’an Natural Science Research Project, School-Level Projects of Jiangsu Vocational College of Electronic Information.
Abstract (Originalsprache)
Particle Swarm Optimization (PSO) faces challenges such as premature convergence, insufficient population diversity, and limited search capability in complex optimization problems. To address these issues, a particle swarm optimization algorithm integrating reinforcement learning and an adaptive regeneration mechanism, termed RLARPSO, is developed. The proposed approach incorporates a neighborhood-best guidance mechanism based on a small-world topology, a reinforcement learning (RL)-driven dynamic acceleration factor adjustment strategy, and a Levy flight-based regeneration mechanism for inferior particles. Performance evaluation is conducted on the CEC2017 benchmark function suite, with comparisons against five representative PSO variants. Experimental results demonstrate that RLARPSO achieves superior convergence accuracy, solution stability, and capability of escaping local optima. Statistical significance tests confirm the reliability of the observed performance differences. Ablation studies further analyze the contribution of each key component to the overall optimization performance, supporting the effectiveness and rationality of the algorithmic design.
Förderung
- Jiangsu Province Colleges and Universities “Qinglan Project”
- Huai’an Natural Science Research Project
- School-Level Projects of Jiangsu Vocational College of Electronic Information
- National Natural Science Foundation of China
- Basic Strengthening Program
Zitieren
APA
Tian, H., Liu, J., & Guan, J. (2026). Particle swarm optimization integrating reinforcement learning and an adaptive regeneration mechanism. AIP Advances, 16(7). https://doi.org/10.1063/5.0343006
Vancouver
Tian H, Liu J, Guan J. Particle swarm optimization integrating reinforcement learning and an adaptive regeneration mechanism. AIP Advances. 2026;16(7). doi:10.1063/5.0343006
BibTeX
@article{Tian2026,
author = {Tian, Han and Liu, Jun and Guan, Jun},
title = {Particle swarm optimization integrating reinforcement learning and an adaptive regeneration mechanism},
journal = {AIP Advances},
year = {2026},
volume = {16},
number = {7},
doi = {10.1063/5.0343006}
}
EUVIMED