Deep reinforcement learning for traffic light optimization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep Reinforcement Learning has the potential of practically addressing one of the most pressing problems in road traffic management, namely that of traffic light optimization (TLO). The objective of the TLO problem is to set the timings (phase and duration) of traffic lights in order to minimize the overall travel time of the vehicles that traverse the road network. In this paper, we introduce a new reward function that is able to decrease travel time in a micro-simulator environment. More specifically, our reward function simultaneously takes the traffic flow and traffic delay into account in order to provide a solution to the TLO problem. We use both Deep Q-Learning and Policy Gradient approaches to solve the resulting reinforcement learning problem.

Original languageEnglish
Title of host publicationProceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
EditorsJeffrey Yu, Zhenhui Li, Hanghang Tong, Feida Zhu
PublisherIEEE Computer Society
Pages564-571
Number of pages8
ISBN (Electronic)9781538692882
DOIs
Publication statusPublished - 7 Feb 2019
Event18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 - Singapore, Singapore
Duration: 17 Nov 201820 Nov 2018

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
Volume2018-November
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

Conference18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
CountrySingapore
CitySingapore
Period17/11/1820/11/18

Fingerprint

Reinforcement learning
Telecommunication traffic
Travel time
Simulators

Keywords

  • Deep Learning
  • Traffic Light Optimization

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Coskun, M., Baggag, A., & Chawla, S. (2019). Deep reinforcement learning for traffic light optimization. In J. Yu, Z. Li, H. Tong, & F. Zhu (Eds.), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 (pp. 564-571). [8637414] (IEEE International Conference on Data Mining Workshops, ICDMW; Vol. 2018-November). IEEE Computer Society. https://doi.org/10.1109/ICDMW.2018.00088

Deep reinforcement learning for traffic light optimization. / Coskun, Mustafa; Baggag, Abdelkader; Chawla, Sanjay.

Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. ed. / Jeffrey Yu; Zhenhui Li; Hanghang Tong; Feida Zhu. IEEE Computer Society, 2019. p. 564-571 8637414 (IEEE International Conference on Data Mining Workshops, ICDMW; Vol. 2018-November).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Coskun, M, Baggag, A & Chawla, S 2019, Deep reinforcement learning for traffic light optimization. in J Yu, Z Li, H Tong & F Zhu (eds), Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018., 8637414, IEEE International Conference on Data Mining Workshops, ICDMW, vol. 2018-November, IEEE Computer Society, pp. 564-571, 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018, Singapore, Singapore, 17/11/18. https://doi.org/10.1109/ICDMW.2018.00088
Coskun M, Baggag A, Chawla S. Deep reinforcement learning for traffic light optimization. In Yu J, Li Z, Tong H, Zhu F, editors, Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. IEEE Computer Society. 2019. p. 564-571. 8637414. (IEEE International Conference on Data Mining Workshops, ICDMW). https://doi.org/10.1109/ICDMW.2018.00088
Coskun, Mustafa ; Baggag, Abdelkader ; Chawla, Sanjay. / Deep reinforcement learning for traffic light optimization. Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. editor / Jeffrey Yu ; Zhenhui Li ; Hanghang Tong ; Feida Zhu. IEEE Computer Society, 2019. pp. 564-571 (IEEE International Conference on Data Mining Workshops, ICDMW).
@inproceedings{edd212d440774a43b9d1e02131047b54,
title = "Deep reinforcement learning for traffic light optimization",
abstract = "Deep Reinforcement Learning has the potential of practically addressing one of the most pressing problems in road traffic management, namely that of traffic light optimization (TLO). The objective of the TLO problem is to set the timings (phase and duration) of traffic lights in order to minimize the overall travel time of the vehicles that traverse the road network. In this paper, we introduce a new reward function that is able to decrease travel time in a micro-simulator environment. More specifically, our reward function simultaneously takes the traffic flow and traffic delay into account in order to provide a solution to the TLO problem. We use both Deep Q-Learning and Policy Gradient approaches to solve the resulting reinforcement learning problem.",
keywords = "Deep Learning, Traffic Light Optimization",
author = "Mustafa Coskun and Abdelkader Baggag and Sanjay Chawla",
year = "2019",
month = "2",
day = "7",
doi = "10.1109/ICDMW.2018.00088",
language = "English",
series = "IEEE International Conference on Data Mining Workshops, ICDMW",
publisher = "IEEE Computer Society",
pages = "564--571",
editor = "Jeffrey Yu and Zhenhui Li and Hanghang Tong and Feida Zhu",
booktitle = "Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018",

}

TY - GEN

T1 - Deep reinforcement learning for traffic light optimization

AU - Coskun, Mustafa

AU - Baggag, Abdelkader

AU - Chawla, Sanjay

PY - 2019/2/7

Y1 - 2019/2/7

N2 - Deep Reinforcement Learning has the potential of practically addressing one of the most pressing problems in road traffic management, namely that of traffic light optimization (TLO). The objective of the TLO problem is to set the timings (phase and duration) of traffic lights in order to minimize the overall travel time of the vehicles that traverse the road network. In this paper, we introduce a new reward function that is able to decrease travel time in a micro-simulator environment. More specifically, our reward function simultaneously takes the traffic flow and traffic delay into account in order to provide a solution to the TLO problem. We use both Deep Q-Learning and Policy Gradient approaches to solve the resulting reinforcement learning problem.

AB - Deep Reinforcement Learning has the potential of practically addressing one of the most pressing problems in road traffic management, namely that of traffic light optimization (TLO). The objective of the TLO problem is to set the timings (phase and duration) of traffic lights in order to minimize the overall travel time of the vehicles that traverse the road network. In this paper, we introduce a new reward function that is able to decrease travel time in a micro-simulator environment. More specifically, our reward function simultaneously takes the traffic flow and traffic delay into account in order to provide a solution to the TLO problem. We use both Deep Q-Learning and Policy Gradient approaches to solve the resulting reinforcement learning problem.

KW - Deep Learning

KW - Traffic Light Optimization

UR - http://www.scopus.com/inward/record.url?scp=85062884930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062884930&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2018.00088

DO - 10.1109/ICDMW.2018.00088

M3 - Conference contribution

T3 - IEEE International Conference on Data Mining Workshops, ICDMW

SP - 564

EP - 571

BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018

A2 - Yu, Jeffrey

A2 - Li, Zhenhui

A2 - Tong, Hanghang

A2 - Zhu, Feida

PB - IEEE Computer Society

ER -