{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:14:59Z","timestamp":1783527299029,"version":"3.55.0"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/ivs.2018.8500675","type":"proceedings-article","created":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T00:56:23Z","timestamp":1540256183000},"page":"1227-1232","source":"Crossref","is-referenced-by-count":43,"title":["Highway Traffic Modeling and Decision Making for Autonomous Vehicle Using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Changxi","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitar","family":"Filev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panagiotis","family":"Tsiotras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref30","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref10","article-title":"Continuous curvature path generation based on Bézier curves for autonomous vehicles","volume":"40","author":"choi","year":"2010","journal-title":"International Journal of Applied Mathematics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728533"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.09.011"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/978-0-387-84858-7_2","article-title":"Overview of supervised learning","author":"hastie","year":"2009","journal-title":"The Elements of Statistical Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref15","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning-An Introduction MIT Press Cambridge"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3182\/20100712-3-DE-2013.00006"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525162"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798354"},{"key":"ref28","article-title":"Learning from delayed rewards","author":"watkins","year":"1989","journal-title":"Ph D dissertation King’s College Cambridge"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2008.2012116"},{"key":"ref27","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proceedings of the 17th International Conference on Machine Learning"},{"key":"ref3","first-page":"1537","article-title":"Probabilistic MDPbehavior planning for cars","author":"brechtel","year":"2011","journal-title":"14th International IEEE Conference on Intelligent Transportation Systems (ITSC)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/34.3900"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1994.343737"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.1995.528266"},{"key":"ref2","article-title":"Long-term planning by short-term prediction","author":"shalev-shwartz","year":"2016","journal-title":"arXiv preprint arXiv 1602 04875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WCECS.2008.27"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"6","DOI":"10.3390\/machines5010006","article-title":"Perception, planning, control, and coordination for autonomous vehicles","volume":"5","author":"pendleton","year":"2017","journal-title":"Machines"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref22","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref24","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","author":"levine","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"92","article-title":"Human behavior modeling with maximum entropy inverse optimal control","author":"ziebart","year":"2009","journal-title":"AAAI Spring Symposium on Human Behavior Modeling"},{"key":"ref26","article-title":"Maximum entropy deep inverse reinforcement learning","author":"wulfmeier","year":"2015","journal-title":"arXiv preprint arXiv 1507 04888"},{"key":"ref25","article-title":"Continuous inverse optimal control with locally optimal examples","author":"levine","year":"2012","journal-title":"arXiv preprint arXiv 1206 4617"}],"event":{"name":"2018 IEEE Intelligent Vehicles Symposium (IV)","location":"Changshu","start":{"date-parts":[[2018,6,26]]},"end":{"date-parts":[[2018,6,30]]}},"container-title":["2018 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8472796\/8500355\/08500675.pdf?arnumber=8500675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:17:25Z","timestamp":1643217445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8500675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/ivs.2018.8500675","relation":{},"subject":[],"published":{"date-parts":[[2018,6]]}}}