Please use this identifier to cite or link to this item:
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Civil and Environmental Engineeringen_US
dc.contributorDepartment of Land Surveying and Geo-Informaticsen_US
dc.creatorHu, Zen_US
dc.creatorZhuge, Cen_US
dc.creatorMa, Wen_US
dc.rightsPosted with permission of the RL4ITS Workshop.en_US
dc.titleTowards a very large scale traffic simulator for multi-agent reinforcement learning testbedsen_US
dc.typeConference Paperen_US
dcterms.abstractSmart traffic control and management become an emerging application for Deep Reinforcement Learning (DRL) to solve traffic congestion prob lems in urban networks. Different traffic con trol and management policies can be tested on the traffic simulation. Current DRL-based studies are mainly supported by the microscopic simulation software (e.g., SUMO1), while it is not suitable for city-wide control due to the computational burden and gridlock effect. To the best of our knowledge, there is a lack of studies on the large-scale traffic simulator for DRL testbeds, which could further hinder the development of DRL. In view of this, we propose a meso-macro traffic simulator for very large-scale DRL scenarios. The proposed simulator integrates mesoscopic and macroscopic traffic sim ulation model to improve efficiency and eliminate gridlocks. The mesoscopic link model simulates flow dynamics on roads, and the macroscopic Bath tub model depicts vehicle movement in regions. Moreover, both types of models can be hybridized to accommodate various DRL tasks. This creates portals for mixed transportation applications under different contexts. The result shows that the de veloped simulator only takes 46 seconds to finish a 24-hour simulation in a very large city with 2.2 million vehicles, which is much faster than SUMO. Additionally, we develop a graphic interface for users to visualize the simulation results in a web explorer. In the future, the developed meso-macro traffic simulator could serve as a new environment for very large-scale DRL problems.en_US
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationPaper presented in IJCAI 2021 Reinforcement Learning for Intelligent Transportation Systems (RL4ITS) Workshop, August 21, 2021, Virtual Eventen_US
dc.relation.conferenceReinforcement Learning for Intelligent Transportation Systems (RL4ITS) Workshopen_US
dc.description.validate202110 bcwhen_US
dc.description.oaOther Versionen_US
dc.description.fundingTextP0033933, P0036472en_US
Appears in Collections:Conference Paper
Files in This Item:
File Description SizeFormat 
2365_IJCAI21_ITS_Workshop_camera_ready.pdf1.15 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Other Version
Show simple item record

Page views

Citations as of Jul 3, 2022


Citations as of Jul 3, 2022

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.