Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

167 Downloads (Pure)

Abstract

Reinforcement learning (RL) constitutes a promising solution for alleviating the problem of traffic congestion. In particular, deep RL algorithms have been shown to produce adaptive traffic signal controllers that outperform conventional systems. However, in order to be reliable in highly dynamic urban areas, such controllers need to be robust with the respect to a series of exogenous sources of uncertainty. In this paper, we develop an open-source callback-based framework for promoting the flexible evaluation of different deep RL configurations under a traffic simulation environment. With this framework, we investigate how deep RL-based adaptive traffic controllers perform under different scenarios, namely under demand surges caused by special events, capacity reductions from incidents and sensor failures. We extract several key insights for the development of robust deep RL algorithms for traffic control and propose concrete designs to mitigate the impact of the considered exogenous uncertainties.
Original languageEnglish
Title of host publicationProceedings of the IEEE Intelligent Transportation Systems Conference (ITSC) 2019
Number of pages8
PublisherIEEE
Publication date2019
ISBN (Electronic)978-1-5386-7024-8
DOIs
Publication statusPublished - 2019
Event22nd International IEEE Conference on Intelligent Transportation Systems - Conference Venue Cordis Hotel, Auckland, New Zealand
Duration: 27 Oct 201930 Oct 2019
Conference number: 22
https://ieeexplore.ieee.org/xpl/conhome/8907344/proceeding

Conference

Conference22nd International IEEE Conference on Intelligent Transportation Systems
Number22
LocationConference Venue Cordis Hotel
Country/TerritoryNew Zealand
CityAuckland
Period27/10/201930/10/2019
Internet address

Fingerprint

Dive into the research topics of 'Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failures'. Together they form a unique fingerprint.

Cite this