A Reinforcement Learning Approach for Traffic Control

被引:3
作者
Baumgart, Urs [1 ]
Burger, Michael [1 ]
机构
[1] Fraunhofer Inst Ind Math ITWM, Fraunhofer Pl 1, D-67663 Kaiserslautern, Germany
来源
PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON VEHICLE TECHNOLOGY AND INTELLIGENT TRANSPORT SYSTEMS (VEHITS) | 2021年
关键词
Reinforcement Learning; Traffic Control; Microscopic Traffic Models; Radial Basis Function Networks; WAVES; FLOW; GO;
D O I
10.5220/0010448501330141
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Intelligent traffic control is a key tool to achieve and to realize resource-efficient and sustainable mobility solutions. In this contribution, we study a promising data-based control approach, reinforcement learning (RL), and its applicability to traffic flow problems in a virtual environment. We model different traffic networks using the microscopic traffic simulation software SUMO. RL-methods are used to teach controllers, so called RL agents, to guide certain vehicles or to control a traffic light system. The agents obtain real-time information from other vehicles and learn to improve the traffic flow by repetitive observation and algorithmic optimization. As controller models, we consider both simple linear models and non-linear radial basis function networks. The latter allow to include prior knowledge from the training data and a two-step training procedure leading to an efficient controller training.
引用
收藏
页码:133 / 141
页数:9
相关论文
共 36 条
[1]  
[Anonymous], 2002, HDB MARKOV DECISION
[2]   Reinforcement learning-based multi-agent system for network traffic signal control [J].
Arel, I. ;
Liu, C. ;
Urbanik, T. ;
Kohls, A. G. .
IET INTELLIGENT TRANSPORT SYSTEMS, 2010, 4 (02) :128-135
[3]  
ASAM, 2020, ASAM OPENDRIVE
[4]   Expert Level Control of Ramp Metering Based on Multi-Task Deep Reinforcement Learning [J].
Belletti, Francois ;
Haziza, Daniel ;
Gomes, Gabriel ;
Bayen, Alexandre M. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2018, 19 (04) :1198-1207
[5]  
Bishop Christopher M, 2006, PATTERN RECOGN, V128, P1, DOI [10.1117/1.2819119, DOI 10.1117/1]
[6]  
Chae H, 2017, IEEE INT C INTELL TR
[7]   Optimal Traffic Light Control for a Single Intersection [J].
De Schutter, B. ;
De Moor, B. .
EUROPEAN JOURNAL OF CONTROL, 1998, 4 (03) :260-276
[8]  
Deisenroth M. P., 2010, THESIS KIT
[9]  
Duan Y, 2016, PR MACH LEARN RES, V48
[10]  
Foley M., 2022, INTERACT LEARN ENVIR, DOI [10.22541/au.165540488.82174026/v1, DOI 10.1080/10494820.2020.1813178]