{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:40:03Z","timestamp":1778258403206,"version":"3.51.4"},"reference-count":18,"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\/itsc.2019.8917304","type":"proceedings-article","created":{"date-parts":[[2019,11,29]],"date-time":"2019-11-29T11:11:50Z","timestamp":1575025910000},"page":"3810-3815","source":"Crossref","is-referenced-by-count":22,"title":["Multi-Reward Architecture based Reinforcement Learning for Highway Driving Policies"],"prefix":"10.1109","author":[{"given":"Wei","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuesheng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref11","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":"ref12","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015"},{"key":"ref15","first-page":"5","article-title":"Deep reinforcement learning with double q-learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"AAAI"},{"key":"ref16","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"End-to-end deep reinforcement learning for lane keeping assist","author":"sallab","year":"2016"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref4","article-title":"End to end learning for self-driving cars","author":"bojarski","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_27"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.376"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref2","author":"pomerleau","year":"1989","journal-title":"ALVINN An Autonomous Land Vehicle in a Neural Network"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500645"},{"key":"ref9","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"}],"event":{"name":"2019 IEEE Intelligent Transportation Systems Conference - ITSC","location":"Auckland, New Zealand","start":{"date-parts":[[2019,10,27]]},"end":{"date-parts":[[2019,10,30]]}},"container-title":["2019 IEEE Intelligent Transportation Systems Conference (ITSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8907344\/8916833\/08917304.pdf?arnumber=8917304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:46:13Z","timestamp":1658155573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8917304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/itsc.2019.8917304","relation":{},"subject":[],"published":{"date-parts":[[2019,10]]}}}