{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:39:52Z","timestamp":1774967992776,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T00:00:00Z","timestamp":1660953600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,20]],"date-time":"2022-08-20T00:00:00Z","timestamp":1660953600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,20]]},"DOI":"10.1109\/case49997.2022.9926499","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:58:44Z","timestamp":1667523524000},"page":"675-682","source":"Crossref","is-referenced-by-count":8,"title":["A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles"],"prefix":"10.1109","author":[{"given":"Ivan","family":"Masmitja","sequence":"first","affiliation":[{"name":"Mbari,Bioinspiration Lab,CA,USA,95062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"Martin","sequence":"additional","affiliation":[{"name":"Universitat Politècnica de Catalunya, Barcelona Tech.,Knowledge Engineering and Machine Learning Group,Barcelona,Spain,08034"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kakani","family":"Katija","sequence":"additional","affiliation":[{"name":"Mbari,Bioinspiration Lab,CA,USA,95062"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spartacus","family":"Gomariz","sequence":"additional","affiliation":[{"name":"Barcelona Tech.,Sarti Research Group,Electronics Department Universitat Politècnica de Catalunya,Barcelona,Spain,080934"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joan","family":"Navarro","sequence":"additional","affiliation":[{"name":"Institut de Ciències del Mar,Csic,Barcelona,Spain,08003"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-019-1091-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app10041256"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.391242"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2009.4752682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/501480a"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AUV.1998.744434"},{"key":"ref7","first-page":"1","article-title":"Underwater acoustic positioning systems based on buoys with gps","volume-title":"Proceedings of the Eighth European Conference on Underwater Acoustics","volume":"8","author":"Alcocer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924722"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/s16091491"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2909133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OCEANSE.2017.8084996"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1201\/9780203026786"},{"key":"ref13","volume-title":"Detection, estimation, and modulation theory, part I: detection, estimation, and linear modulation theory","author":"Van Trees","year":"2004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2015.2494918"},{"key":"ref15","first-page":"1","article-title":"Accuracy analysis for tdoa localization in sensor networks","volume-title":"14th International Conference on Information Fusion","author":"Kaune"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918802351"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.10.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc3701"},{"key":"ref19","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref20","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0533-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2939-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27015-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971780"},{"key":"ref26","article-title":"Marine control systems: guidance, navigation and control of ships, rigs and underwater vehicles","author":"Fossen","year":"2002","journal-title":"Marine Cybernetics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s18041241"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abl4925"},{"key":"ref29","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Lowe"},{"key":"ref30","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","author":"Terry","year":"2020"},{"key":"ref31","first-page":"267","article-title":"Range-only underwater target localization : error characterization","volume-title":"\"21st IMEKO TC4 International Symposium and 19th International Workshop on ADC Modelling and Testing Understanding the World through Electrical and Electronic Measurement","author":"Masmitja"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-99982-7"},{"key":"ref34","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019"},{"key":"ref35","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"key":"ref36","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref37","article-title":"Don\u2019t decay the learning rate, increase the batch size","author":"Smith","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/48.775299"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CACSD-CCA-ISIC.2006.4776912"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3182\/20100915-3-DE-3008.00056"},{"key":"ref41","article-title":"Deep reinforcement learning at the edge of the statistical precipice","volume-title":"Part of Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)","author":"Agarwal"}],"event":{"name":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","location":"Mexico City, Mexico","start":{"date-parts":[[2022,8,20]]},"end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9926286\/9926419\/09926499.pdf?arnumber=9926499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T06:18:31Z","timestamp":1706077111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9926499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,20]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/case49997.2022.9926499","relation":{},"subject":[],"published":{"date-parts":[[2022,8,20]]}}}