A multi process value-based reinforcement learning environment framework for adaptive traffic signal control

doi:10.1080/23307706.2022.2041115

CORC > 兰州理工大学 > 兰州理工大学

	A multi process value-based reinforcement learning environment framework for adaptive traffic signal control
	Cao, Jie 1,2; Huang, Dailin 1; Hou, Liang 1; Ma, Jialin 1
刊名	Journal of Control and Decision
	2022
关键词	Computer aided instruction Memory architecture Process control Program processors Reinforcement learning Traffic congestion Adaptive traffic signal control Multi-Processes Process methods Process values Sampling efficiency Shared memory Simulation of urban mobility Single process Urban mobility Value-based
ISSN号	2330-7706
DOI	10.1080/23307706.2022.2041115
英文摘要	Realising adaptive traffic signal control (ATSC) through reinforcement learning (RL) is an important means to easetraffic congestion. This paper finds the computing power of the central processing unit (CPU) cannot fully usedwhen Simulation of Urban MObility (SUMO) is used as an environment simulator for RL. We propose a multi-process framework under value-basedRL. First, we propose a shared memory mechanism to improve exploration efficiency. Second, we use the weight sharing mechanism to solve the problem of asynchronous multi-process agents. We also explained the reason shared memory in ATSC does not lead to early local optima of the agent. We have verified in experiments the sampling efficiency of the 10-process method is 8.259 times that of the single process. The sampling efficiency of the 20-process method is 13.409 times that of the single process. Moreover, the agent can also converge to the optimal solution. © 2022 Northeastern University, China.
语种	英语
出版者	Taylor and Francis Ltd.
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/159098]
专题	兰州理工大学
作者单位	1.College of Computer and Communication, Lanzhou University of Technology, Lanzhou, China; 2.Engineering Research Center of Manufacturing Information of Gansu Province, Lanzhou, China
推荐引用方式 GB/T 7714	Cao, Jie,Huang, Dailin,Hou, Liang,et al. A multi process value-based reinforcement learning environment framework for adaptive traffic signal control[J]. Journal of Control and Decision,2022.
APA	Cao, Jie,Huang, Dailin,Hou, Liang,&Ma, Jialin.(2022).A multi process value-based reinforcement learning environment framework for adaptive traffic signal control.Journal of Control and Decision.
MLA	Cao, Jie,et al."A multi process value-based reinforcement learning environment framework for adaptive traffic signal control".Journal of Control and Decision (2022).