{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:47:15Z","timestamp":1781675235966,"version":"3.54.5"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T00:00:00Z","timestamp":1657324800000},"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":[[2022,7,9]]},"DOI":"10.1109\/icarm54641.2022.9959167","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:31:50Z","timestamp":1669732310000},"page":"386-391","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Target Following Control for Autonomous Vehicles with Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Linhai","family":"Li","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Intelligent Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Intelligent Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiping","family":"Shi","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Intelligent Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Intelligent Science and Technology,Changsha,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref11","first-page":"1078","article-title":"Self-learning cruise control using kernel-based least squares policy iteration","author":"wang","year":"2013","journal-title":"IEEE Transactions on Control Systems Technology"},{"key":"ref12","first-page":"2903","article-title":"Training drift counteraction optimal control policies using reinforcement learning: An adaptive cruise control example","author":"li","year":"2017","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9030110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113816"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-0507(05)80172-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref18","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"ICML"},{"key":"ref19","first-page":"1","article-title":"CARLA: An open urban driving simulator","author":"dosovitskiy","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref4","first-page":"2089","article-title":"A portable vision-based real-time lane departure warning system: day and night","author":"hsiao","year":"2008","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.51.1035"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2013.10.008"},{"key":"ref8","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref7","author":"xie","year":"2017","journal-title":"arXiv preprint arXiv 1706 09829"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2006.869597"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00423110903365910"},{"key":"ref9","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2022 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Guilin, China","start":{"date-parts":[[2022,7,9]]},"end":{"date-parts":[[2022,7,11]]}},"container-title":["2022 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9959088\/9959097\/09959167.pdf?arnumber=9959167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T15:01:33Z","timestamp":1671462093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9959167\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,9]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icarm54641.2022.9959167","relation":{},"subject":[],"published":{"date-parts":[[2022,7,9]]}}}