Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Xinren, Cheng, Sixi, Zhong, Zixin, Yu, Jiadong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908584278753280
author Zhang, Xinren
Cheng, Sixi
Zhong, Zixin
Yu, Jiadong
author_facet Zhang, Xinren
Cheng, Sixi
Zhong, Zixin
Yu, Jiadong
contents Multi-agent systems (MAS) solve complex problems through coordinated autonomous entities with individual decision-making capabilities. While Multi-Agent Reinforcement Learning (MARL) enables these agents to learn intelligent strategies, it faces challenges of non-stationarity and partial observability. Communications among agents offer a solution, but questions remain about its optimal structure and evaluation. This paper explores two underexamined aspects: communication topology and information efficiency. We demonstrate that directed and sequential topologies improve performance while reducing communication overhead across both homogeneous and heterogeneous tasks. Additionally, we introduce two metrics -- Information Entropy Efficiency Index (IEI) and Specialization Efficiency Index (SEI) -- to evaluate message compactness and role differentiation. Incorporating these metrics into training objectives improves success rates and convergence speed. Our findings highlight that designing adaptive communication topologies with information-efficient messaging is essential for effective coordination in complex MAS.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07888
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL
Zhang, Xinren
Cheng, Sixi
Zhong, Zixin
Yu, Jiadong
Multiagent Systems
Multi-agent systems (MAS) solve complex problems through coordinated autonomous entities with individual decision-making capabilities. While Multi-Agent Reinforcement Learning (MARL) enables these agents to learn intelligent strategies, it faces challenges of non-stationarity and partial observability. Communications among agents offer a solution, but questions remain about its optimal structure and evaluation. This paper explores two underexamined aspects: communication topology and information efficiency. We demonstrate that directed and sequential topologies improve performance while reducing communication overhead across both homogeneous and heterogeneous tasks. Additionally, we introduce two metrics -- Information Entropy Efficiency Index (IEI) and Specialization Efficiency Index (SEI) -- to evaluate message compactness and role differentiation. Incorporating these metrics into training objectives improves success rates and convergence speed. Our findings highlight that designing adaptive communication topologies with information-efficient messaging is essential for effective coordination in complex MAS.
title Network Topology and Information Efficiency of Multi-Agent Systems: Study based on MARL
topic Multiagent Systems
url https://arxiv.org/abs/2510.07888