{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T12:23:07Z","timestamp":1785241387483,"version":"3.55.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41427806"],"award-info":[{"award-number":["41427806"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/tnnls.2018.2884797","type":"journal-article","created":{"date-parts":[[2018,12,28]],"date-time":"2018-12-28T19:38:05Z","timestamp":1546025885000},"page":"3534-3546","source":"Crossref","is-referenced-by-count":102,"title":["Multi Pseudo Q-Learning-Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8677-0011","authenticated-orcid":false,"given":"Wenjie","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0858-1770","authenticated-orcid":false,"given":"Shiji","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8611-2665","authenticated-orcid":false,"given":"Cheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994138"},{"key":"ref38","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2654539"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref37","author":"sutton","year":"2011","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref36","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref35","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref34","first-page":"1","article-title":"Target following for an autonomous underwater vehicle using regularized ELM-based reinforcement learning","author":"sun","year":"2015","journal-title":"Proc OCEANS'05 MTS\/IEEE Washington"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.1993.236372"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1575\/1912\/3040"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2013.01.029"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2400427"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2010.07.006"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2363073"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2411285"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2429555"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2557223"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2554621"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2012.2227719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2465352"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2007.916347"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/OCEANS.2015.7401861"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/TSMCB.2012.2210212","article-title":"Dynamic task assignment and path planning of multi-AUV system based on an improved self-organizing map and velocity synthesis method in three-dimensional underwater workspace","volume":"43","author":"zhu","year":"2013","journal-title":"IEEE Trans Cybern"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.04.029"},{"key":"ref29","first-page":"1","article-title":"Parameterized batch reinforcement learning for longitudinal control of autonomous land vehicles","author":"huang","year":"2017","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2697447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2500027"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-016-1004-4"},{"key":"ref1","article-title":"Control of autonomous underwater vehicles","author":"singh","year":"2011"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4031\/MTSJ.50.1.4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2399020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2516948"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.4236\/ica.2016.74012"},{"key":"ref24","article-title":"Reinforcement learning applied to the control of an autonomous underwater vehicle","author":"gaskett","year":"1999","journal-title":"Proc Australian Conf Robotics Automation"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2016.1540"},{"key":"ref44","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.11.009"},{"key":"ref43","article-title":"A method for stochastic optimization","volume":"5","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2004.835805"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8930649\/08594674.pdf?arnumber=8594674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:49:29Z","timestamp":1657745369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594674\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":44,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2884797","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}