A Graph Attention Mechanism Based Multi-Agent Reinforcement Learning Method for Efficient Traffic Light Control

Su, Changqing; Yan, Yan; Wang, Tao; Zhang, Baoxian; Li, Cheng

doi:10.1109/iwcmc51323.2021.9498671

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al proposed a model that decomposed intersections into subgraphs such that subgraphs, rather than entire graphs, were learned synchronously, thereby significantly reducing the learning time [12]. Su et al proposed a multiagent reinforcement learning algorithm combined with an attention mechanism for a large-scale traffic signal control problem [13]. Zeng extracted the features of dynamic traffic networks using graph convolutional networks and used the states of neighboring A2C agents to learn cooperative control policies [14].…”

Section: Related Researchmentioning

confidence: 99%

Learning Thresholds to Select Cooperative Partners by Applying Deep Reinforcement Learning in Distributed Traffic Signal Control

Matsuta¹,

Kodama²,

Harada³

EPiC Series in Computing

View full text Add to dashboard Cite

One method to reduce vehicle congestion in a road traffic network is to appropriately control traffic signals. One control scheme for traffic signals is a distributed control scheme in which individual traffic signals cooperate locally with other geographically close traffic signals. Deep reinforcement learning has been actively studied to appropriately control traffic signals. In distributed control, it is important to select appropriate cooperative partners. In this study, we propose a method for selecting appropriate cooperative partners using deep reinforcement learning to the distributed traffic signal control.

show abstract

Section: Related Researchmentioning

confidence: 99%