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[3,4,5];Sugawara, Toshiharu[6];Tang, Yang[2]

机构：[1]East China Univ Sci & Technol, Sch Math, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[3]Zhejiang Normal Univ, Sch Math Sci, Jinhua 321004, Peoples R China;[4]Zhejiang Normal Univ, Hangzhou Sch Automat, Hangzhou 311231, Peoples R China;[5]Zhejiang Normal Univ, China Mozamb Belt & Rd Joint Lab Smart Agr, Jinhua 321004, Peoples R China;[6]Waseda Univ, Dept Comp Sci & Commun Engn, Tokyo, Japan

年份：2026

卷号：36

期号：2

外文期刊名：CHAOS

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001694287400001)】；

基金：This work was supported by the National Natural Science Foundation of China under Grant Nos. 62233005, U2441245, U25B6002, and 62573198, the Shanghai Aerospace Science and Technology Innovation Fund under Grant No. SAST2024-060, the Shanghai Institute for Mathematics and Interdisciplinary Sciences (SIMIS) under Grant No. SIMIS-ID-2025-SP, the Shanghai Baiyulan Talent Program Pujiang Project under Grant No. 25PJD023, the Natural Science Foundation of Zhejiang Province of China under Grant No. LRG25F030002, the Zhejiang Province Leading Geese Plan under Grant No. 2025C01056, the National Key Laboratory of Space Intelligent Control under Grant No. HTKJ2024KL502004, the National Key Laboratory of Information Systems Engineering under Grant No. WDZC20265290405, the National Key Laboratory of Space Target Awareness under Grant No. STA2025ZCB0208, and the Program of Introducing Talents of Discipline to Universities (the 111 Project) under Grant No. B17017.

语种：英文

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.