{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:46:09Z","timestamp":1784303169911,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014188","name":"\u2018Development of Polar Region Communication Technology and Equipment for Internet of Extreme Things (IoET),\u2019 funded by the Ministry of Science and ICT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3128516","type":"journal-article","created":{"date-parts":[[2021,11,16]],"date-time":"2021-11-16T20:31:06Z","timestamp":1637094666000},"page":"154578-154599","source":"Crossref","is-referenced-by-count":35,"title":["Reinforcement Learning-Based Routing Protocol for Underwater Wireless Sensor Networks: A Comparative Survey"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9662-6056","authenticated-orcid":false,"given":"Rehenuma Tasnim","family":"Rodoshi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-7271","authenticated-orcid":false,"given":"Yujae","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7834-4044","authenticated-orcid":false,"given":"Wooyeol","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-012-0119-9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2015.09.003"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/128757"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2017.2686558"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891590"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2918865"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-008-0096-3"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.3030695"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21937-5_1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913776"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3071490"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s20185393"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1007\/s10776-019-00463-6","article-title":"A survey and performance evaluation of reinforcement learning based spectrum aware routing in cognitive radio ad hoc networks","volume":"27","author":"raj","year":"2020","journal-title":"Int J Wireless Inf Netw"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058388"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/s21082829"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/dac.2455"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2992759"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3390\/en11061471"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.10.022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/Oceans-Spain.2011.6003477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.06.005"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2014.08.012"},{"key":"ref66","year":"2021","journal-title":"The Network Simulator-ns-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMTECH.2018.8722370"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.2012.2197271"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1347364.1347372"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2911694"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2005.01.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928876"},{"key":"ref20","first-page":"1","article-title":"A survey of machine learning in wireless sensor netoworks from networking and application perspectives","author":"di","year":"2007","journal-title":"Proc Int Conf Info Commun Signal Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s19194256"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7321974"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2011.06.009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7539751"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s16030414"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/iet-wss.2013.0118"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3209582.3209610"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1177\/1550147718754728"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICTCK.2014.7033528"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/s20041025"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2989924"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2923425"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2932126"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933968"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013970"},{"key":"ref52","article-title":"QL-EEBDG: QLearning based energy balanced routing in underwater sensor networks","volume":"5","author":"karim","year":"2018","journal-title":"EAI Endorsed Transactions Energy Web"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2618841"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s20082261"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-013-9093-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2011.6162571"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1117\/1.3280288"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7321970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2012.2194670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2664099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.070912.111943"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/Oceans-Spain.2011.6003580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2552538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4031\/002533208786861326"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2011.6162571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2009.4752682"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/48.820738"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/s17071660"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4031\/002533208786861263"},{"key":"ref46","first-page":"243","article-title":"An alternative softmax operator for reinforcement learning","author":"asadi","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-9007-0"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2012.6275781"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1109\/TMC.2010.28","article-title":"QELAR: A machine-learning-based adaptive routing protocol for energy-efficient and lifetime-extended underwater sensor networks","volume":"9","author":"hu","year":"2010","journal-title":"IEEE Trans Mobile Comput"},{"key":"ref42","article-title":"Tight performance bounds on greedy policies based on imperfect value functions","author":"williams","year":"1993"},{"key":"ref41","first-page":"903","article-title":"Practical reinforcement learning in continuous spaces","author":"smart","year":"2000","journal-title":"Proc ICML"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.431"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09615209.pdf?arnumber=9615209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T20:55:09Z","timestamp":1643057709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9615209\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3128516","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}