PMARL: Multi-Agent Reinforcement Learning in Large-Scale Systems
ACM Transactions on Intelligent Systems and Technology · 30.06.2026 · 17 (3) · 1-19
DOI: 10.1145/3799229 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 27.04.2026. Verfasst von Baofu Fang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Natural Science Foundation of Anhui Province, Advanced Materials–National Science and Technology Major Project, China University Industry–Academia–Research Innovation Fund.
Abstract (Originalsprache)
Large-scale multi-agent systems face two core challenges: inefficient policy learning and the explosion of state dimensions. Existing methods often rely on manually designed task sequences to guide agents’ learning in stages, but these designs lack adaptability to agents’ learning abilities, making it difficult to ensure the rationality of task difficulty. Moreover, the representation capability of current network structures is limited, making it challenging to efficiently handle high-dimensional state information and complex interaction relationships. To address these issues, we propose a Progressive Multi-Agent Reinforcement Learning (PMARL) framework. PMARL introduces a task adapter that adaptively selects task difficulty based on agents’ learning abilities, eliminating reliance on manual experience. Additionally, a Dynamic Dimension Adaptive Network (DDAN) is designed, incorporating hypernetwork and self-attention mechanisms to achieve adaptive feature extraction of high-dimensional states and efficient representation of agent interaction relationships. Experimental results demonstrate that PMARL exhibits higher efficiency and better adaptability compared to existing methods when addressing large-scale multi-agent tasks.
Förderung
- Natural Science Foundation of Anhui Province
- Advanced Materials–National Science and Technology Major Project
- China University Industry–Academia–Research Innovation Fund
- University Synergy Innovation Program of Anhui Province
- Open Fund of the Key Laboratory of Flight Techniques and Flight Safety, CAAC
Zitieren
APA
Fang, B., Wang, Q., Wang, H., Yu, K., & Wang, Z. (2026). PMARL: Multi-Agent Reinforcement Learning in Large-Scale Systems. ACM Transactions on Intelligent Systems and Technology, 17(3), 1-19. https://doi.org/10.1145/3799229
Vancouver
Fang B, Wang Q, Wang H, Yu K, Wang Z. PMARL: Multi-Agent Reinforcement Learning in Large-Scale Systems. ACM Transactions on Intelligent Systems and Technology. 2026;17(3):1-19. doi:10.1145/3799229
BibTeX
@article{Fang2026,
author = {Fang, Baofu and Wang, Qiong and Wang, Hao and Yu, Kui and Wang, Zaijun},
title = {PMARL: Multi-Agent Reinforcement Learning in Large-Scale Systems},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2026},
volume = {17},
number = {3},
pages = {1--19},
doi = {10.1145/3799229}
}
EUVIMED