Multi-Agent Broad Reinforcement Learning for Intelligent Traffic Light Control

TL;DR

This paper introduces a novel Multi-Agent Broad Reinforcement Learning framework for traffic light control, leveraging broad networks for faster training and better agent interaction modeling, showing improved results over existing methods.

Contribution

The paper proposes a new MABRL framework that models each agent with broad networks and introduces a dynamic interaction mechanism, addressing limitations of existing MADRL and BRL approaches.

Findings

MABRL outperforms six baseline approaches in traffic light control tasks.

Experimental results on three datasets demonstrate the effectiveness of MABRL.

The approach reduces training time compared to traditional MADRL methods.

Abstract

Intelligent Traffic Light Control System (ITLCS) is a typical Multi-Agent System (MAS), which comprises multiple roads and traffic lights.Constructing a model of MAS for ITLCS is the basis to alleviate traffic congestion. Existing approaches of MAS are largely based on Multi-Agent Deep Reinforcement Learning (MADRL). Although the Deep Neural Network (DNN) of MABRL is effective, the training time is long, and the parameters are difficult to trace. Recently, Broad Learning Systems (BLS) provided a selective way for learning in the deep neural networks by a flat network. Moreover, Broad Reinforcement Learning (BRL) extends BLS in Single Agent Deep Reinforcement Learning (SADRL) problem with promising results. However, BRL does not focus on the intricate structures and interaction of agents. Motivated by the feature of MADRL and the issue of BRL, we propose a Multi-Agent Broad Reinforcement Learning (MABRL) framework to explore the function of BLS in MAS. Firstly, unlike most existing MADRL approaches, which use a series of deep neural networks structures, we model each agent with broad networks. Then, we introduce a dynamic self-cycling interaction mechanism to confirm the "3W" information: When to interact, Which agents need to consider, What information to transmit. Finally, we do the experiments based on the intelligent traffic light control scenario. We compare the MABRL approach with six different approaches, and experimental results on three datasets verify the effectiveness of MABRL.