{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:25:05Z","timestamp":1791566705062,"version":"4.3.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197132","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"5385-5392","source":"Crossref","is-referenced-by-count":91,"title":["Driving in Dense Traffic with Model-Free Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Dhruv Mauria","family":"Saxena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangjae","family":"Bae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Nakhaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kikuo","family":"Fujimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxim","family":"Likhachev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5654369"},{"key":"ref31","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016","journal-title":"CoRR abs\/1610 03295"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105157"},{"key":"ref37","first-page":"2061","article-title":"A real-time motion planner with trajectory optimization for autonomous vehicles","author":"xu","year":"2012","journal-title":"2012 IEEE International Conference on Robotics and Automation ICRA"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995727"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2015.349"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77074-9_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref13","article-title":"Model-predictive policy learning with uncertainty regularization for driving in dense traffic","author":"henaff","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364906075328"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968478"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.aau5872","article-title":"Learning agile and dynamic motor skills for legged robots","volume":"4","author":"hwangbo","year":"2019","journal-title":"Robotics Science"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.09.011"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref4","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016","journal-title":"CoRR abs\/1604 07316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.029"},{"key":"ref3","article-title":"Cooperation-aware lane change control in dense traffic","author":"bae","year":"2019","journal-title":"CoRR abs\/1909 05665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989224"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-03991-1","article-title":"The DARPA Urban Challenge: Autonomous Vehicles in City Traffic, George Air Force Base","volume":"56","author":"buehler","year":"2009","journal-title":"Springer Tracts in Advanced Robotics"},{"key":"ref8","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","author":"chou","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning volume 70 of Proceedings of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594386"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593813"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2015.7225830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2011.5940562"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995721"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2389215"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref26","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"1989","journal-title":"Advances in Neural Information Processing Systems 1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197132.pdf?arnumber=9197132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:20:49Z","timestamp":1656375649000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197132","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}