Robust and Efficient Communication in Multi-Agent Reinforcement Learning

TL;DR

This paper reviews recent advances in robust and efficient communication strategies for multi-agent reinforcement learning, addressing real-world constraints like delays, bandwidth limits, and message perturbations to improve practical deployment.

Contribution

It systematically surveys communication methods in MARL under realistic constraints and highlights open challenges and future directions for practical multi-agent systems.

Findings

Addresses communication robustness in MARL under real-world conditions

Highlights applications in autonomous driving, SLAM, and federated learning

Identifies key open challenges and research directions

Abstract

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.