Robust Event-Triggered Integrated Communication and Control with Graph Information Bottleneck Optimization

TL;DR

This paper introduces CDE-GIB, a novel method combining graph information bottleneck and event-triggered communication to improve multi-agent reinforcement learning efficiency and consensus accuracy under partial observability.

Contribution

It proposes a new consensus-driven event-based GIB approach with a variable-threshold mechanism to reduce communication load and enhance collaboration in multi-agent systems.

Findings

Outperforms state-of-the-art methods in efficiency.

Achieves better adaptability in multi-agent tasks.

Reduces communication volume significantly.

Abstract

Integrated communication and control serves as a critical ingredient in Multi-Agent Reinforcement Learning. However, partial observability limitations will impair collaboration effectiveness, and a potential solution is to establish consensus through well-calibrated latent variables obtained from neighboring agents. Nevertheless, the rigid transmission of less informative content can still result in redundant information exchanges. Therefore, we propose a Consensus-Driven Event-Based Graph Information Bottleneck (CDE-GIB) method, which integrates the communication graph and information flow through a GIB regularizer to extract more concise message representations while avoiding the high computational complexity of inner-loop operations. To further minimize the communication volume required for establishing consensus during interactions, we also develop a variable-threshold event-triggering mechanism. By simultaneously considering historical data and current observations, this mechanism capably evaluates the importance of information to determine whether an event should be triggered. Experimental results demonstrate that our proposed method outperforms existing state-of-the-art methods in terms of both efficiency and adaptability.