Deep Reinforcement Learning for Addressing Disruptions in Traffic Light Control

作     者：Faizan Rasheed Kok-Lim Alvin Yau Rafidah Md Noor Yung-Wey Chong 

作者机构：School of Engineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computing and Information SystemsSunway UniversitySubang Jaya47500Malaysia Faculty of Computer Science and Information TechnologyUniversity of MalayaKuala Lumpur50603Malaysia National Advanced IPv6 CentreUniversiti Sains MalaysiaUSMPenang11800Malaysia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第71卷第5期

页      面：2225-2247页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 

基　　金：Universiti Sains Malaysia 

主　　题：Artificial intelligence traffic light control traffic disruptions multi-agent deep Q-network deep reinforcement learning 

摘      要：This paper investigates the use of multi-agent deep Q-network(MADQN)to address the curse of dimensionality issue occurred in the traditional multi-agent reinforcement learning(MARL)*** proposed MADQN is applied to traffic light controllers at multiple intersections with busy traffic and traffic disruptions,particularly *** is based on deep Q-network(DQN),which is an integration of the traditional reinforcement learning(RL)and the newly emerging deep learning(DL)*** enables traffic light controllers to learn,exchange knowledge with neighboring agents,and select optimal joint actions in a collaborative manner.A case study based on a real traffic network is conducted as part of a sustainable urban city project in the Sunway City of Kuala Lumpur in *** is also performed using a grid traffic network(GTN)to understand that the proposed scheme is effective in a traditional traffic *** proposed scheme is evaluated using two simulation tools,namely Matlab and Simulation of Urban Mobility(SUMO).Our proposed scheme has shown that the cumulative delay of vehicles can be reduced by up to 30%in the simulations.