Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

2019-11-16 · ICML 2020 1 · Rundong Wang, Xu He, Runsheng Yu, Wei Qiu, Bo An, Zinovi Rabinovich

We consider the problem of the limited-bandwidth communication for multi-agent reinforcement learning, where agents cooperate with the assistance of a communication protocol and a scheduler. The protocol and scheduler jointly determine which agent is communicating what message and to whom. Under the limited bandwidth constraint, a communication protocol is required to generate informative messages. Meanwhile, an unnecessary communication connection should not be established because it occupies limited resources in vain. In this paper, we develop an Informative Multi-Agent Communication (IMAC) method to learn efficient communication protocols as well as scheduling. First, from the perspective of communication theory, we prove that the limited bandwidth constraint requires low-entropy messages throughout the transmission. Then inspired by the information bottleneck principle, we learn a valuable and compact communication protocol and a weight-based scheduler. To demonstrate the efficiency of our method, we conduct extensive experiments in various cooperative and competitive multi-agent tasks with different numbers of agents and different bandwidths. We show that IMAC converges faster and leads to efficient communication among agents under the limited bandwidth as compared to many baseline methods.

📄 PDF Abstract BibTeX arXiv:1911.06992

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning Reinforcement LearningScheduling

CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning

2021-12-20 · Qi Tian, Kun Kuang, Baoxiang Wang, Furui Liu 외

Communication is one of the core components for cooperative multi-agent reinforcement learning (MARL). The communication bandwidth, in many real applications, is always subject to certain constraints. To improve communic…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)Starcraft+1

Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization

2026-02-02 · Ahmad Farooq, Kamran Iqbal arxiv

Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness. We present a framework that combines inf…

Multi-agent Reinforcement Learning

Towards Human-Agent Communication via the Information Bottleneck Principle

2022-06-30 · Mycal Tucker, Julie Shah, Roger Levy, Noga Zaslavsky

Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficiently compress meanings into communicatio…

Informativeness

InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck

2025-12-11 · Quanmin Wei, Penglin Dai, Wei Li, Bingyi Liu 외 arxiv

Precise environmental perception is critical for the reliability of autonomous driving systems. While collaborative perception mitigates the limitations of single-agent perception through information sharing, it encounte…

Autonomous Driving

Generalization Bounds of Emergent Communications for Agentic AI Networking

2026-05-09 · Yong Xiao, Jingxuan Chai, Guangming Shi, Ping Zhang arxiv

The evolution of 6G networking toward agentic AI networking (AgentNet) systems requires a shift from traditional data pipelines to task-aware, agentic AI-native communication solutions. Emergent communication, a novel co…