{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:01Z","timestamp":1767339361523,"version":"3.44.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8967612","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"5869-5874","source":"Crossref","is-referenced-by-count":17,"title":["End-to-end sensorimotor control problems of AUVs with deep reinforcement learning"],"prefix":"10.1109","author":[{"given":"Hui","family":"Wu","sequence":"first","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P.R.China"}]},{"given":"Shiji","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P.R.China"}]},{"given":"Yachu","family":"Hsu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P.R.China"}]},{"given":"Keyou","family":"You","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P.R.China"}]},{"given":"Cheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,P.R.China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2016.06.041"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2465352"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2779442"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885374"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IRCE.2018.8492943"},{"key":"ref15","article-title":"Marine control system-guidance, navigation and control of ships, rigs and underwater vehicles","author":"fossen","year":"2002","journal-title":"Marine Cybemetics"},{"key":"ref16","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2001.968766"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385788"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.64"},{"key":"ref3","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref6","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460934"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2316\/Journal.206.2012.3.206-3690"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5772\/64065"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"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":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-015-2551-x"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2019,11,3]]},"location":"Macau, China","end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08967612.pdf?arnumber=8967612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:41Z","timestamp":1755800621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8967612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8967612","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}