{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T15:15:02Z","timestamp":1772291702365,"version":"3.50.1"},"reference-count":56,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/itsc.2017.8317694","type":"proceedings-article","created":{"date-parts":[[2018,3,15]],"date-time":"2018-03-15T16:47:12Z","timestamp":1521132432000},"page":"1-8","source":"Crossref","is-referenced-by-count":28,"title":["Framework for control and deep reinforcement learning in traffic"],"prefix":"10.1109","author":[{"given":"Cathy","family":"Wu","sequence":"first","affiliation":[]},{"given":"Kanaad","family":"Parvate","sequence":"additional","affiliation":[]},{"given":"Nishant","family":"Kheterpal","sequence":"additional","affiliation":[]},{"given":"Leah","family":"Dickstein","sequence":"additional","affiliation":[]},{"given":"Ankur","family":"Mehta","sequence":"additional","affiliation":[]},{"given":"Eugene","family":"Vinitsky","sequence":"additional","affiliation":[]},{"given":"Alexandre M","family":"Bayen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_2"},{"key":"ref38","first-page":"1","article-title":"Vissim: A microscopic simulation tool to evaluate actuated signal control including bus priority","author":"fellendorf","year":"1994","journal-title":"64th Meeting of Institute of Transportation Engineers"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2345663"},{"key":"ref32","author":"vinyals","year":"2016","journal-title":"Deepmind and blizzard to release starcraft ii as an ai research environment"},{"key":"ref31","author":"wymann","year":"2000","journal-title":"TORCS The Open Racing Car Simulator"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00128098"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2010.10.004"},{"key":"ref35","author":"belletti","year":"2017","journal-title":"Expert level control of ramp metering based on multi-task deep reinforcement learning"},{"key":"ref34","author":"polson","year":"2016","journal-title":"Deep learning predictors for traffic flows"},{"key":"ref28","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref27","author":"beattie","year":"2016","journal-title":"Deepmind lab"},{"key":"ref29","author":"synnaeve","year":"2016","journal-title":"Torchcraft a library for machine learning research on real-time strategy games"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.819610"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32460-4"},{"key":"ref20","article-title":"Optimal coordinated and integrated motorway network traffic control","author":"kotsialos","year":"1999","journal-title":"14th International Symposium on Transportation and Traffic Theory"},{"key":"ref22","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref21","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref24","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1613\/jair.3912","article-title":"The arcade learning environment: An evaluation platform for general agents","volume":"47","author":"bellemare","year":"2013","journal-title":"J Artif Intell Res (JAIR)"},{"key":"ref25","author":"lai","year":"2015","journal-title":"Giraffe Using deep reinforcement learning to play chess"},{"key":"ref50","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"NIPS"},{"key":"ref51","author":"duan","year":"2016","journal-title":"Benchmarking deep reinforcement learning for continuous control"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/10\/3\/033001"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-3-319-15024-6_7","article-title":"SUMO's lane-changing model","author":"erdmann","year":"2015","journal-title":"Modeling Mobility with Open Data"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1631\/jzus.A0900370"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3141\/2088-08"},{"key":"ref52","author":"dowling","year":"2004","journal-title":"Traffic analysis toolbox volume iii Guidelines for applying traffic microsimulation modeling software"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2292500"},{"key":"ref11","article-title":"String stability of interconnected systems: An application to platooning in automated highway systems","author":"swaroop","year":"1997","journal-title":"California Partners for Advanced Transit and Highways (PATH)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2010.0205"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2011-48829"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.trc.2014.04.014","article-title":"Dynamics of connected vehicle systems with delayed acceleration feedback","volume":"46","author":"jin","year":"2014","journal-title":"Transportation Research Part C Emerging Technologies"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728204"},{"key":"ref16","article-title":"Eigenvalue and eigenvector analysis of stability for a line of traffic","author":"wang","year":"2016","journal-title":"Studies in Applied Mathematics"},{"key":"ref17","article-title":"Stabilizing traffic with autonomous vehicles","author":"wu","year":"2017","journal-title":"Submission"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S1369-8478(00)00005-X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2013.11.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2003.821292"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/25.260745"},{"key":"ref6","article-title":"Dynamic ecodriving in northern california: A study of survey and vehicle operations data from an ecodriving feedback device","author":"martin","year":"2013","journal-title":"Transportation Research Board Annu Meeting"},{"key":"ref5","year":"2010","journal-title":"Intelligent transport systems Intelligent transport systems — Adaptive Cruise Control systems — Performance requirements and test procedures"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2003.821340"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1299\/jsmec.43.671"},{"key":"ref49","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2005.844226"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref45","author":"bellman","year":"1957","journal-title":"A Markovian Decision Process"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.1035"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/BF03167222"},{"key":"ref42","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":"ref41","doi-asserted-by":"crossref","DOI":"10.5334\/baw","author":"horni","year":"2016","journal-title":"Multi-Agent Transportation SIMulation"},{"key":"ref44","year":"2016","journal-title":"Simulation\/basic definition"},{"key":"ref43","year":"2016","journal-title":"Car Following Models"}],"event":{"name":"2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)","location":"Yokohama","start":{"date-parts":[[2017,10,16]]},"end":{"date-parts":[[2017,10,19]]}},"container-title":["2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8307147\/8317580\/08317694.pdf?arnumber=8317694","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T19:58:19Z","timestamp":1570910299000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8317694\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/itsc.2017.8317694","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}