Parallel Reinforcement Learning for Traffic Signal Control

James Duggan

doi:10.1016/j.procs.2015.05.172

Parallel Reinforcement Learning for Traffic Signal Control

James Duggan

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

Abstract

Developing Adaptive Traffic Signal Control strategies for efficient urban traffic management is a challenging problem, which is not easily solved. Reinforcement Learning (RL) has been shown to be a promising approach when applied to traffic signal control (TSC) problems. When using RL agents for TSC, difficulties may arise with respect to convergence times and performance. This is especially pronounced on complex intersections with many different phases, due to the increased size of the state action space. Parallel Learning is an emerging technique in RL literature, which allows several learning agents to pool their experiences while learning concurrently on the same problem. Here we present an extension to a leading published work on RL for TSC, which leverages the benefits of Parallel Learning to increase exploration and reduce delay times and queue lengths. (C) 2015 The Authors. Published by Elsevier B.V.

Original language	English (Ireland)
Title of host publication	6TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT-2015), THE 5TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2015)
DOIs	https://doi.org/10.1016/j.procs.2015.05.172
Publication status	Published - 1 Jan 2015

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Authors (Note for portal: view the doc link for the full list of authors)

Authors
Mannion, P,Duggan, J,Howley, E,Shakshuki, E

Access to Document

10.1016/j.procs.2015.05.172

Cite this

@inproceedings{413fe80b98504f48b0b83c73c70ba2f6,

title = "Parallel Reinforcement Learning for Traffic Signal Control",

abstract = "Developing Adaptive Traffic Signal Control strategies for efficient urban traffic management is a challenging problem, which is not easily solved. Reinforcement Learning (RL) has been shown to be a promising approach when applied to traffic signal control (TSC) problems. When using RL agents for TSC, difficulties may arise with respect to convergence times and performance. This is especially pronounced on complex intersections with many different phases, due to the increased size of the state action space. Parallel Learning is an emerging technique in RL literature, which allows several learning agents to pool their experiences while learning concurrently on the same problem. Here we present an extension to a leading published work on RL for TSC, which leverages the benefits of Parallel Learning to increase exploration and reduce delay times and queue lengths. (C) 2015 The Authors. Published by Elsevier B.V.",

author = "James Duggan",

year = "2015",

month = jan,

day = "1",

doi = "10.1016/j.procs.2015.05.172",

language = "English (Ireland)",

booktitle = "6TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT-2015), THE 5TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2015)",

}

Parallel Reinforcement Learning for Traffic Signal Control. / Duggan, James.
6TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT-2015), THE 5TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2015). 2015.

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Parallel Reinforcement Learning for Traffic Signal Control

AU - Duggan, James

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Developing Adaptive Traffic Signal Control strategies for efficient urban traffic management is a challenging problem, which is not easily solved. Reinforcement Learning (RL) has been shown to be a promising approach when applied to traffic signal control (TSC) problems. When using RL agents for TSC, difficulties may arise with respect to convergence times and performance. This is especially pronounced on complex intersections with many different phases, due to the increased size of the state action space. Parallel Learning is an emerging technique in RL literature, which allows several learning agents to pool their experiences while learning concurrently on the same problem. Here we present an extension to a leading published work on RL for TSC, which leverages the benefits of Parallel Learning to increase exploration and reduce delay times and queue lengths. (C) 2015 The Authors. Published by Elsevier B.V.

AB - Developing Adaptive Traffic Signal Control strategies for efficient urban traffic management is a challenging problem, which is not easily solved. Reinforcement Learning (RL) has been shown to be a promising approach when applied to traffic signal control (TSC) problems. When using RL agents for TSC, difficulties may arise with respect to convergence times and performance. This is especially pronounced on complex intersections with many different phases, due to the increased size of the state action space. Parallel Learning is an emerging technique in RL literature, which allows several learning agents to pool their experiences while learning concurrently on the same problem. Here we present an extension to a leading published work on RL for TSC, which leverages the benefits of Parallel Learning to increase exploration and reduce delay times and queue lengths. (C) 2015 The Authors. Published by Elsevier B.V.

U2 - 10.1016/j.procs.2015.05.172

DO - 10.1016/j.procs.2015.05.172

M3 - Conference Publication

BT - 6TH INTERNATIONAL CONFERENCE ON AMBIENT SYSTEMS, NETWORKS AND TECHNOLOGIES (ANT-2015), THE 5TH INTERNATIONAL CONFERENCE ON SUSTAINABLE ENERGY INFORMATION TECHNOLOGY (SEIT-2015)

ER -

Parallel Reinforcement Learning for Traffic Signal Control

Abstract

UN SDGs

Authors (Note for portal: view the doc link for the full list of authors)

Access to Document

Fingerprint

Cite this