{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:32:44Z","timestamp":1783603964530,"version":"3.55.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51809246"],"award-info":[{"award-number":["51809246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2018QF003"],"award-info":[{"award-number":["ZR2018QF003"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2970433","type":"journal-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T21:32:02Z","timestamp":1580419922000},"page":"24258-24268","source":"Crossref","is-referenced-by-count":110,"title":["Deep Interactive Reinforcement Learning for Path Following of Autonomous Underwater Vehicle"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3285-8602","authenticated-orcid":false,"given":"Qilei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8019-9758","authenticated-orcid":false,"given":"Jinying","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0292-3231","authenticated-orcid":false,"given":"Qixin","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6826-4721","authenticated-orcid":false,"given":"Bo","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2016.7761080"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)37809-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-017-9374-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650873"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-5659-9_7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2645699"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref17","article-title":"Learning from human-generated reward","author":"knox","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02675-6_46"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9283-7"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9308-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2017.8028138"},{"key":"ref27","first-page":"586","article-title":"A direct adaptive method for faster backpropagation learning: The RPROP algorithm","author":"riedmiller","year":"2002","journal-title":"Proc IEEE Int Conf Neural Netw"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref29","article-title":"Social interaction for efficient agent learning from human reward","author":"li","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2019.2912447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/37.272779","article-title":"Learning control for underwater robotic vehicles","volume":"14","author":"yuh","year":"1994","journal-title":"IEEE Control Syst"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1109\/TCST.2005.847331","article-title":"PID control system analysis, design, and technology","volume":"13","author":"ang","year":"2005","journal-title":"IEEE Trans Control Syst Technol"},{"key":"ref20","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume":"70","author":"macglashan","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref22","first-page":"95","article-title":"Learning by demonstration applied to underwater intervention","volume":"269","author":"carrera","year":"2014","journal-title":"Proc 17th Int Conf Catalan Assoc Artif Intell in Frontiers in Artificial Intelligence and Applications"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS-Bergen.2013.6608097"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631235"},{"key":"ref26","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08976170.pdf?arnumber=8976170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:17Z","timestamp":1639770677000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8976170\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2970433","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}