Priority-Driven Control and Communication in Decentralized Multi-Agent Systems via Reinforcement Learning

2026-05-11

AI Summary

This work addresses the challenge of jointly optimizing communication efficiency and event-triggered control in decentralized multi-agent systems when an accurate system model is unavailable. To circumvent the difficulty posed by mixed action spaces in conventional event-triggered control, the paper proposes a model-free, priority-driven reinforcement learning algorithm that introduces a learnable communication prioritization mechanism. This approach enables end-to-end co-optimization of communication and control policies without explicit modeling of the underlying dynamics. Experimental results on standard multi-agent benchmark tasks demonstrate that the proposed method significantly reduces communication overhead while maintaining or even improving control performance, outperforming existing baseline approaches.

Abstract

Event-triggered control provides a mechanism for avoiding excessive use of constrained communication bandwidth in networked multi-agent systems. However, most existing methods rely on accurate system models, which may be unavailable in practice. In this work, we propose a model-free, priority-driven reinforcement learning algorithm that learns communication priorities and control policies jointly from data in decentralized multi-agent systems. By learning communication priorities, we circumvent the hybrid action space typical in event-triggered control with binary communication decisions. We evaluate our algorithm on benchmark tasks and demonstrate that it outperforms the baseline method.

Problem

• decentralized multi-agent systems
• event-triggered control
• communication bandwidth
• model-free
• reinforcement learning

Innovation

• model-free reinforcement learning
• priority-driven control
• decentralized multi-agent systems
• event-triggered communication
• joint policy learning