skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework

Abstract

Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plans in terms of average delay, number of stops, and vehicular emissions at the network level.

Authors:
 [1];  [1];  [1];  [1]
  1. Purdue Univ., West Lafayette, IN (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE, National Science Foundation (NSF)
OSTI Identifier:
1265896
Grant/Contract Number:  
AC05-00OR22725; 1004528; 104IPY04
Resource Type:
Accepted Manuscript
Journal Name:
Transportation Research Part C: Emerging Technologies
Additional Journal Information:
Journal Volume: 58; Journal Issue: PC; Journal ID: ISSN 0968-090X
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Traffic Control; Learning Algorithm; Multi-agent control; Connected Vehicle

Citation Formats

Zhu, Feng, Aziz, H. M. Abdul, Qian, Xinwu, and Ukkusuri, Satish V. A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework. United States: N. p., 2015. Web. doi:10.1016/j.trc.2014.12.009.
Zhu, Feng, Aziz, H. M. Abdul, Qian, Xinwu, & Ukkusuri, Satish V. A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework. United States. doi:10.1016/j.trc.2014.12.009.
Zhu, Feng, Aziz, H. M. Abdul, Qian, Xinwu, and Ukkusuri, Satish V. Sat . "A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework". United States. doi:10.1016/j.trc.2014.12.009. https://www.osti.gov/servlets/purl/1265896.
@article{osti_1265896,
title = {A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework},
author = {Zhu, Feng and Aziz, H. M. Abdul and Qian, Xinwu and Ukkusuri, Satish V.},
abstractNote = {Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plans in terms of average delay, number of stops, and vehicular emissions at the network level.},
doi = {10.1016/j.trc.2014.12.009},
journal = {Transportation Research Part C: Emerging Technologies},
number = PC,
volume = 58,
place = {United States},
year = {2015},
month = {1}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 4 works
Citation information provided by
Web of Science

Save / Share: