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

TL;DR

This paper introduces a model-free reinforcement learning approach for decentralized multi-agent systems that learns communication priorities and control policies jointly, improving efficiency without relying on accurate models.

Contribution

It presents a novel priority-driven RL algorithm that handles hybrid actions and outperforms baseline methods in benchmark tasks.

Findings

The proposed method effectively learns communication priorities and control policies.

It outperforms baseline methods in benchmark multi-agent tasks.

The approach avoids the need for accurate system models.

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.