Attn-CommNet: Coordinated Traffic Lights Control On Large-Scale Network Level

Gao, Jiashi; Shi, Xinming; Yu, James J. Q.

10.1109/ICTAI52525.2021.00048

2021

IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI)

1082-3409

978-1-6654-0899-8

2021 IEEE 33RD INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2021)

2021-November

289-293

NOV 01-03, 2021

null,null,ELECTR NETWORK

10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA

IEEE COMPUTER SOC

Traffic lights control could be regarded as a multi-agent coordinated problem. A model-free reinforcement learning (RL) approach is a powerful framework for solving such coordinated policy-making problems without prior environmental knowledge. In order to approach a global policy, communication among agents needs to be built. To enable dynamic and scalable communication, we propose a new RL model, CommNet based on Local Attention Mechanism (Attn-CommNet), which uses local selection and attention mechanism between hidden layers to facilitate cooperation. We evaluated the proposed method using synthetic and real word traffic flows under multi-scale road networks. The results demonstrate that the proposed method can get better performance in multi-scale problems, especially large-scale problems compared to the state-of-the-art methods.

reinforcement learning multi-agent control coordinated traffic lights control

第一 ; 通讯

英语

CPCI-S ; EI

Stable Support Plan Program of Shenzhen Natural Science Fund[20200925155105002] ; General Program of Guangdong Basic and Applied Basic Research Foundation[2019A1515011032]

Computer Science

Computer Science, Artificial Intelligence

WOS:000747482300040

20220611591878

Reinforcement learning

Artificial Intelligence:723.4

Web of Science

Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Peoples R China

Gao, Jiashi,Shi, Xinming,Yu, James J. Q.. Attn-CommNet: Coordinated Traffic Lights Control On Large-Scale Network Level[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE COMPUTER SOC,2021:289-293.