{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:44:00Z","timestamp":1783784640637,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":[[2019,10]]},"DOI":"10.1109\/smc.2019.8914621","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T10:09:34Z","timestamp":1575022174000},"page":"2326-2331","source":"Crossref","is-referenced-by-count":118,"title":["Autonomous Highway Driving using Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Subramanya","family":"Nageshrao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H. Eric","family":"Tseng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitar","family":"Filev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","first-page":"77","article-title":"Lane-changing model in sumo","volume":"24","author":"erdmann","year":"2014","journal-title":"Proceedings of the SUMO2014 Modeling Mobility with Open Data"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3141\/1999-10"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref10","first-page":"1437","article-title":"A comprehensive survey on safe rein-forcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","article-title":"Safe reinforcement learning via shielding","author":"alshiekh","year":"2017","journal-title":"arXiv preprint arXiv 1708 02562"},{"key":"ref12","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv preprint arXiv 1511 05952"},{"key":"ref13","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref14","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv preprint arXiv 1710 02298"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref16","article-title":"Meta learning shared hierarchies","author":"frans","year":"2017","journal-title":"arXiv preprint arXiv 1710 09767"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3761"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3141\/1999-08"},{"key":"ref4","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0001-4575(00)00019-1"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref29","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11796","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref7","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","volume":"16","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref2","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"},{"key":"ref9","article-title":"On a formal model of safe and scalable self-driving cars","author":"shalev-shwartz","year":"2017","journal-title":"arXiv preprint arXiv 1708 06374"},{"key":"ref1","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":"ref20","article-title":"End-to-end learning of driving models with surround-view cameras and route planners","author":"hecker","year":"2018","journal-title":"European Conference on Computer Vision (ECCV)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2017-5209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref23","article-title":"Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems","author":"li","year":"2017","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"ref26","article-title":"Analytical and experimental study of automated lane change control based on lane centering algorithms","author":"ivanovic","year":"2017","journal-title":"Internal technical report Ford Motor Company"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2003.821292"}],"event":{"name":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","location":"Bari, Italy","start":{"date-parts":[[2019,10,6]]},"end":{"date-parts":[[2019,10,9]]}},"container-title":["2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8906183\/8913838\/08914621.pdf?arnumber=8914621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T02:51:45Z","timestamp":1665111105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8914621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/smc.2019.8914621","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}