Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning

Hamid Mirzaei; Guni Sharon; Stephen Boyles; Tony Givargis; Peter Stone

doi:10.1109/ITSC.2018.8569737

Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning

Hamid Mirzaei
, Guni Sharon
, Stephen Boyles
, Tony Givargis
, Peter Stone

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Scopus citations

Abstract

In the micro-tolling paradigm, a centralized system manager sets different toll values for each link in a given traffic network with the objective of optimizing the system's performance. A recently proposed micro-tolling scheme, denoted \Delta-tolling, was shown to yield up to 32% reduction in total travel time when compared to a no-toll scheme. \Delta-tolling, computes a toll value for each link in a given network based on two global parameters: \beta which is a proportional parameter and R which controls the rate of toll change over time. In this paper, we propose to generalize \Delta-tolling such that it would consider different R and \beta parameters for each link. a policy gradient reinforcement learning algorithm is used in order to tune this high-dimensional optimization problem. The results show that such a variant of \Delta-tolling far surpasses the original \Delta-tolling scheme, yielding up to 38% reduced system travel time compared to the original \Delta-tolling scheme.

Original language	English
Title of host publication	2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018
Publisher	Institute of Electrical and Electronics Engineers
Pages	47-52
Number of pages	6
ISBN (Electronic)	9781728103235
DOIs	https://doi.org/10.1109/ITSC.2018.8569737
State	Published - 7 Dec 2018
Externally published	Yes
Event	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018 - Maui, United States Duration: 4 Nov 2018 → 7 Nov 2018

Publication series

Name	IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Volume	2018-November
ISSN (Print)	2153-0009
ISSN (Electronic)	2153-0017

Conference

Conference	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018
Country/Territory	United States
City	Maui
Period	4/11/18 → 7/11/18

ASJC Scopus subject areas

Automotive Engineering
Mechanical Engineering
Computer Science Applications

Access to Document

10.1109/ITSC.2018.8569737

Cite this

Mirzaei, H., Sharon, G., Boyles, S., Givargis, T., & Stone, P. (2018). Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning. In 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018 (pp. 47-52). Article 8569737 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2018-November). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ITSC.2018.8569737

@inproceedings{da8485ce90b942939f8b14624b855fe7,

title = "Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning",

abstract = "In the micro-tolling paradigm, a centralized system manager sets different toll values for each link in a given traffic network with the objective of optimizing the system's performance. A recently proposed micro-tolling scheme, denoted \textbackslash{}Delta-tolling, was shown to yield up to 32\% reduction in total travel time when compared to a no-toll scheme. \textbackslash{}Delta-tolling, computes a toll value for each link in a given network based on two global parameters: \textbackslash{}beta which is a proportional parameter and R which controls the rate of toll change over time. In this paper, we propose to generalize \textbackslash{}Delta-tolling such that it would consider different R and \textbackslash{}beta parameters for each link. a policy gradient reinforcement learning algorithm is used in order to tune this high-dimensional optimization problem. The results show that such a variant of \textbackslash{}Delta-tolling far surpasses the original \textbackslash{}Delta-tolling scheme, yielding up to 38\% reduced system travel time compared to the original \textbackslash{}Delta-tolling scheme.",

author = "Hamid Mirzaei and Guni Sharon and Stephen Boyles and Tony Givargis and Peter Stone",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018 ; Conference date: 04-11-2018 Through 07-11-2018",

year = "2018",

month = dec,

day = "7",

doi = "10.1109/ITSC.2018.8569737",

language = "English",

series = "IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "47--52",

booktitle = "2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018",

address = "United States",

}

Mirzaei, H, Sharon, G, Boyles, S, Givargis, T & Stone, P 2018, Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning. in 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018., 8569737, IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, vol. 2018-November, Institute of Electrical and Electronics Engineers, pp. 47-52, 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018, Maui, United States, 4/11/18. https://doi.org/10.1109/ITSC.2018.8569737

Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning. / Mirzaei, Hamid; Sharon, Guni; Boyles, Stephen et al.
2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018. Institute of Electrical and Electronics Engineers, 2018. p. 47-52 8569737 (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC; Vol. 2018-November).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Enhanced Delta-tolling

T2 - 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018

AU - Mirzaei, Hamid

AU - Sharon, Guni

AU - Boyles, Stephen

AU - Givargis, Tony

AU - Stone, Peter

PY - 2018/12/7

Y1 - 2018/12/7

N2 - In the micro-tolling paradigm, a centralized system manager sets different toll values for each link in a given traffic network with the objective of optimizing the system's performance. A recently proposed micro-tolling scheme, denoted \Delta-tolling, was shown to yield up to 32% reduction in total travel time when compared to a no-toll scheme. \Delta-tolling, computes a toll value for each link in a given network based on two global parameters: \beta which is a proportional parameter and R which controls the rate of toll change over time. In this paper, we propose to generalize \Delta-tolling such that it would consider different R and \beta parameters for each link. a policy gradient reinforcement learning algorithm is used in order to tune this high-dimensional optimization problem. The results show that such a variant of \Delta-tolling far surpasses the original \Delta-tolling scheme, yielding up to 38% reduced system travel time compared to the original \Delta-tolling scheme.

AB - In the micro-tolling paradigm, a centralized system manager sets different toll values for each link in a given traffic network with the objective of optimizing the system's performance. A recently proposed micro-tolling scheme, denoted \Delta-tolling, was shown to yield up to 32% reduction in total travel time when compared to a no-toll scheme. \Delta-tolling, computes a toll value for each link in a given network based on two global parameters: \beta which is a proportional parameter and R which controls the rate of toll change over time. In this paper, we propose to generalize \Delta-tolling such that it would consider different R and \beta parameters for each link. a policy gradient reinforcement learning algorithm is used in order to tune this high-dimensional optimization problem. The results show that such a variant of \Delta-tolling far surpasses the original \Delta-tolling scheme, yielding up to 38% reduced system travel time compared to the original \Delta-tolling scheme.

UR - https://www.scopus.com/pages/publications/85060470251

U2 - 10.1109/ITSC.2018.8569737

DO - 10.1109/ITSC.2018.8569737

M3 - Conference contribution

AN - SCOPUS:85060470251

T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC

SP - 47

EP - 52

BT - 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018

PB - Institute of Electrical and Electronics Engineers

Y2 - 4 November 2018 through 7 November 2018

ER -

Mirzaei H, Sharon G, Boyles S, Givargis T, Stone P. Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning. In 2018 IEEE Intelligent Transportation Systems Conference, ITSC 2018. Institute of Electrical and Electronics Engineers. 2018. p. 47-52. 8569737. (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). doi: 10.1109/ITSC.2018.8569737

Enhanced Delta-tolling: Traffic Optimization via Policy Gradient Reinforcement Learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this