Adaptive Traffic Signal Control for large-scale scenario with Cooperative Group-based Multi-agent reinforcement learning

2021 ◽  
Vol 125 ◽  
pp. 103046
Author(s):  
Tong Wang ◽  
Jiahua Cao ◽  
Azhar Hussain
Keyword(s):  
Reinforcement Learning ◽  
Large Scale ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Cooperative Group ◽  
Adaptive Traffic Signal Control ◽  
Multi Agent

scholarly journals Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

2020 ◽  
Vol 21 (3) ◽  
pp. 1086-1095 ◽  
Author(s):  
Tianshu Chu ◽  
Jie Wang ◽  
Lara Codeca ◽  
Zhaojian Li
Keyword(s):  
Reinforcement Learning ◽  
Large Scale ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Multi Agent

scholarly journals Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning

2021 ◽  
Vol 125 ◽  
pp. 103059
Author(s):  
Zhenning Li ◽  
Hao Yu ◽  
Guohui Zhang ◽  
Shangjia Dong ◽  
Cheng-Zhong Xu
Keyword(s):  
Reinforcement Learning ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Control Optimization ◽  
Multi Agent

scholarly journals An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4291 ◽  
Author(s):  
Qiang Wu ◽  
Jianqing Wu ◽  
Jun Shen ◽  
Binbin Yong ◽  
Qingguo Zhou
Keyword(s):  
Reinforcement Learning ◽  
Control Method ◽  
Communication Protocol ◽  
Traffic Signal ◽  
Signal Control ◽  
Traffic Signal Control ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Multi Agent

With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative adaptive global traffic light control method based on multi-agent reinforcement learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC algorithm combines multi-agent auto communication protocol with MARL, allowing an agent to communicate the learned strategies with others for achieving global optimization in traffic signal control. In addition, we present a practicable edge computing architecture for industrial deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth. We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real traffic simulation environment.

Sign in / Sign up

Export Citation Format

Share Document