{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T08:58:25Z","timestamp":1730278705296,"version":"3.28.0"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,19]]},"DOI":"10.1109\/itsc48978.2021.9564699","type":"proceedings-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T15:52:26Z","timestamp":1635177146000},"page":"3813-3820","source":"Crossref","is-referenced-by-count":2,"title":["A Cyber-Physical System for Freeway Ramp Meter Signal Control Using Deep Reinforcement Learning in a Connected Environment"],"prefix":"10.1109","author":[{"given":"Yi","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Graf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Tripp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Biagioni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/TITS.2017.2725912"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICCA.2014.6871097"},{"year":"2018","author":"wu","journal-title":"Differential variable speed limits control for freeway recurrent bottlenecks via deep reinforcement learning","key":"ref33"},{"key":"ref32","article-title":"Development of an efficient driving strategy for connected and automated vehicles at signalized intersections: A reinforcement learning approach","author":"zhou","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref31","article-title":"Distributed multiagent coordinated learning for autonomous driving in highways based on dynamic coordination graphs","author":"yu","year":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1016\/j.trc.2019.08.011"},{"year":"2014","author":"rezaee","journal-title":"Decentralized coordinated optimal ramp metering using multi-agent reinforcement learning","key":"ref37"},{"year":"2019","author":"pandey","journal-title":"Deep reinforcement learning algorithm for dynamic pricing of express lanes with multiple access locations","key":"ref36"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1109\/ITSC.2018.8569317"},{"year":"2019","author":"wu","journal-title":"Es-ctc A deep neuroevolution model for cooperative intelligent freeway traffic control","key":"ref34"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ITSC.2018.8569568"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ITSC.2017.8317839"},{"year":"2002","journal-title":"Temporary Losses of Highway Capacity and Impacts on Performance","key":"ref2"},{"year":"2018","journal-title":"68% of the world population projected to live in urban areas by 2050 says UN","key":"ref1"},{"year":"2020","author":"zhang","journal-title":"Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ITSC.2010.5625066"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TSG.2020.3014055"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TITS.2010.2091408"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TITS.2019.2906260"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1016\/j.trc.2017.09.020"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/TITS.2013.2255286"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1016\/j.trc.2004.08.001"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICMTMA.2011.242"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"year":"0","journal-title":"Connected vehicle benefits","key":"ref12"},{"year":"2013","author":"mnih","journal-title":"Playing atari with deep reinforcement learning","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1177\/0278364913495721"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/s10846-017-0468-y"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TSG.2019.2903756"},{"key":"ref19","article-title":"Restoring Distribution System Under Renewable Uncertainty Using Reinforcement Learning: Preprint","author":"zhang","year":"2020","journal-title":"NREL\/CP-2C00-77116"},{"key":"ref4","first-page":"290","article-title":"Genetic fuzzy logic approach to local ramp metering control using microscopic traffic simulation","author":"yu","year":"2012","journal-title":"2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP) M2VIP"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.3141\/1603-12"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/IVS.2009.5164364"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/MITS.2009.932718"},{"key":"ref8","first-page":"122","article-title":"Freeway ramp control based on single neuron","volume":"2","author":"li","year":"2009","journal-title":"Proc IEEE International Conference on Intelligent Computing and Intelligent Systems"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICIECS.2010.5678377"},{"key":"ref49","article-title":"Second generation of pollutant emission models for sumo","author":"krajzewicz","year":"2014","journal-title":"SUMO2014 - Second SUMO User Conference"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICICTA.2008.259"},{"year":"2017","author":"wu","journal-title":"Flow Architecture and benchmarking for reinforcement learning in traffic control","key":"ref46"},{"year":"2018","author":"horgan","journal-title":"Distributed prioritized experience replay","key":"ref45"},{"year":"2017","author":"liang","journal-title":"Ray rllib A composable and scalable reinforcement learning library","key":"ref48"},{"key":"ref47","first-page":"128","article-title":"Recent development and applications of SUMO - Simulation of Urban MObility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref42","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"year":"1994","author":"rummery","journal-title":"On-line Q-learning using connectionist systems","key":"ref41"},{"key":"ref44","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc International Conference on Machine Learning"},{"year":"2017","author":"schulman","journal-title":"Proximal policy optimization algorithms","key":"ref43"}],"event":{"name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","start":{"date-parts":[[2021,9,19]]},"location":"Indianapolis, IN, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9564393\/9564395\/09564699.pdf?arnumber=9564699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:47:39Z","timestamp":1652183259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9564699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/itsc48978.2021.9564699","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}