{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:25:17Z","timestamp":1782887117909,"version":"3.54.5"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015015","name":"R\u00e9gion Bretagne (France), Government of South Australia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020406","name":"Naval Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020406","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3329136","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T18:23:36Z","timestamp":1698863016000},"page":"123505-123518","source":"Crossref","is-referenced-by-count":13,"title":["Learning Adaptive Control of a UUV Using a Bio-Inspired Experience Replay Mechanism"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1882-0731","authenticated-orcid":false,"given":"Thomas","family":"Chaffre","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8484-0354","authenticated-orcid":false,"given":"Paulo E.","family":"Santos","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0868-2782","authenticated-orcid":false,"given":"Gilles","family":"Le Chenadec","sequence":"additional","affiliation":[{"name":"Lab-STICC UMR CNRS 6285, ENSTA Bretagne, Brest, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Estelle","family":"Chauveau","sequence":"additional","affiliation":[{"name":"Naval Group Research, Ollioules, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7654-9978","authenticated-orcid":false,"given":"Karl","family":"Sammut","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3281-379X","authenticated-orcid":false,"given":"Benoit","family":"Clement","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ahmed"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4gdk"},{"key":"ref3","volume-title":"Adaptive Control","author":"\u00c5str\u00f6m","year":"2008"},{"key":"ref4","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref5","article-title":"Development and commissioning of a DP system for ROV SF 30k","author":"Berg","year":"2012"},{"key":"ref6","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2021.10.113"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0009821603140323"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3387168.3387199"},{"key":"ref10","first-page":"1","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref11","article-title":"An empirical investigation of the challenges of real-world reinforcement learning","author":"Dulac-Arnold","year":"2020","journal-title":"arXiv:2003.11881"},{"key":"ref12","first-page":"1","article-title":"A closer look at deep policy gradients","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ilyas"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANS.2016.7761080"},{"key":"ref14","first-page":"1","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Plappert"},{"key":"ref15","first-page":"1","article-title":"ROS: An open-source robot operating system","volume-title":"Proc. ICRA Workshop Open Source Robot.","author":"Quigley"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2019.0273"},{"key":"ref20","first-page":"1","article-title":"Regularization matters in policy optimization\u2014An empirical study on continuous control","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref21","first-page":"1","article-title":"Revisiting fundamentals of experience replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fedus"},{"key":"ref22","article-title":"Nonlinear modelling and control of underwater vehicles","author":"Fossen","year":"1991"},{"key":"ref23","first-page":"1","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref24","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref25","first-page":"1","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/OCEANS40490.2019.8962598"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.10.401"},{"key":"ref30","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref31","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5962\/bhl.title.55072"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-015-0186-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/ChiCC.2017.8028138"},{"key":"ref40","article-title":"A deeper look at experience replay","author":"Zhang","year":"2017","journal-title":"arXiv:1712.01275"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10304148.pdf?arnumber=10304148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T04:48:44Z","timestamp":1712983724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10304148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3329136","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}