{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T03:10:56Z","timestamp":1794539456509,"version":"4.9.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/vnc48660.2019.9062809","type":"proceedings-article","created":{"date-parts":[[2020,4,14]],"date-time":"2020-04-14T05:55:31Z","timestamp":1586843731000},"page":"1-8","source":"Crossref","is-referenced-by-count":21,"title":["Mixed-Autonomy Traffic Control with Proximal Policy Optimization"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanzhang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lena","family":"Mashayekhy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith","family":"Decker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2017.7959912"},{"key":"ref12","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref13","author":"wu","year":"2017","journal-title":"Flow Architecture and benchmarking for reinforcement learning in traffic control"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CINTI.2013.6705201"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.65"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569307"},{"key":"ref17","author":"liu","year":"2018","journal-title":"Deep reinforcement learning for intelligent transportation systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569615"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2682421"},{"key":"ref27","first-page":"561","article-title":"Ray: A distributed framework for emerging AI applications","author":"moritz","year":"0","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00423119508969108"},{"key":"ref6","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.02.005"},{"key":"ref8","first-page":"1","article-title":"Decentralised reinforcement learning for ramp metering and variable speed limits on highways","volume":"14","author":"schmidt-dumont","year":"2015","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/VNC.2017.8275620"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2687620"},{"key":"ref1","author":"downs","year":"2004","journal-title":"Traffic Why It's Getting Worse What Government Can Do"},{"key":"ref20","first-page":"1","article-title":"Traffic jams without bottlenecksex- perimental evidence for the physical mechanism of the formation of a jam","volume":"10","author":"sugiyama","year":"0","journal-title":"New Journal of Physics"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICITE.2018.8492537"},{"key":"ref21","author":"lin","year":"2018","journal-title":"An efficient deep reinforcement learning model for urban traffic control"},{"key":"ref24","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","author":"vinitsky","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref26","author":"liang","year":"2017","journal-title":"Ray rllib A composable and scalable reinforcement learning library"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"}],"event":{"name":"2019 IEEE Vehicular Networking Conference (VNC)","location":"Los Angeles, CA, USA","start":{"date-parts":[[2019,12,4]]},"end":{"date-parts":[[2019,12,6]]}},"container-title":["2019 IEEE Vehicular Networking Conference (VNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9047648\/9062769\/09062809.pdf?arnumber=9062809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T15:16:24Z","timestamp":1658157384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9062809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/vnc48660.2019.9062809","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}