Multi-Agent Reinforcement Learning based on Two-Step Neighborhood Experience for Traffic Light Control

2021 ◽  
Author(s):  
Yu-Chen Luo ◽  
Chun-Wei Tsai
Keyword(s):  
Reinforcement Learning ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
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.

Multi-Agent Deep Reinforcement Learning for Urban Traffic Light Control in Vehicular Networks

2020 ◽  
Vol 69 (8) ◽  
pp. 8243-8256 ◽  
Author(s):  
Tong Wu ◽  
Pan Zhou ◽  
Kai Liu ◽  
Yali Yuan ◽  
Xiumin Wang ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Vehicular Networks ◽  
Urban Traffic ◽  
Light Control ◽  
Traffic Light ◽  
Traffic Light Control ◽  
Multi Agent

Proposed Traffic Light Control Mechanism Based on Multi-Agent Coordination

2016 ◽  
Vol 20 (5) ◽  
pp. 803-812
Author(s):  
Satoshi Kurihara ◽  
◽  
Ryo Ogawa ◽  
Kosuke Shinoda ◽  
Hirohiko Suwa ◽  
...  
Keyword(s):  
Traffic Flow ◽  
Urban Areas ◽  
Transport Systems ◽  
Light Control ◽  
Traffic Light ◽  
Agent Based ◽  
Traffic Lights ◽  
Control Framework ◽  
Traffic Light Control ◽  
Multi Agent

Traffic congestion is a serious problem for people living in urban areas, causing social problems such as time loss, economical loss, and environmental pollution. Therefore, we propose a multi-agent-based traffic light control framework for intelligent transport systems. Achieving consistent traffic flow necessitates the real-time adaptive coordination of traffic lights; however, many conventional approaches are of the centralized control type and do not have this feature. Our multi-agent-based control framework combines both indirect and direct coordination. Reaction to dynamic traffic flow is attained by indirect coordination, whereas green-wave formation, which is a systematic traffic flow control strategy involving several traffic lights, is attained by direct coordination. We present the detailed mechanism of our framework and verify its effectiveness using simulation to carry out a comparative evaluation.

Sign in / Sign up

Export Citation Format

Share Document