文献类型：期刊文献

英文题名：Robust and Efficient Communication in Multi-Agent Reinforcement Learning

作者：Liu, Zejiao[1]; Li, Yi[2]; Wang, Jiali[2]; Tu, Junqi[2]; Hong, Yitian[2]; Li, Fangfei[1]; Liu, Yang[3,4]; Sugawara, Toshiharu[5]; Tang, Yang[2]

机构：[1] Department of Mathematics, East China University of Science and Technology, Shanghai, 200237, China; [2] Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China; [3] School of Mathematical Sciences, Zhejiang Normal Univerity, Jinhua, 321004, China; [4] Hangzhou School of Automation, Zhejiang Normal University, Hangzhou, 311231, China; [5] Department of Computer Science, Waseda University, Tokyo, Japan

年份：2025

外文期刊名：arXiv

收录：EI(收录号：20250540673)

语种：英文

外文关键词：Agents - Autonomous agents - Bandwidth - Cooperative communication - Data reliability - Data Sharing - Intelligent agents - Machine learning - Multi agent systems

摘要：Multi-agent reinforcement learning (MARL) has made significant strides in enabling coordinated behaviors among autonomous agents. However, most existing approaches assume that communication is instantaneous, reliable, and has unlimited bandwidth; these conditions are rarely met in real-world deployments. This survey systematically reviews recent advances in robust and efficient communication strategies for MARL under realistic constraints, including message perturbations, transmission delays, and limited bandwidth. Furthermore, because the challenges of low-latency reliability, bandwidth-intensive data sharing, and communication-privacy trade-offs are central to practical MARL systems, we focus on three applications involving cooperative autonomous driving, distributed simultaneous localization and mapping, and federated learning. Finally, we identify key open challenges and future research directions, advocating a unified approach that co-designs communication, learning, and robustness to bridge the gap between theoretical MARL models and practical implementations. ? 2025, CC BY-NC-SA.