{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T10:26:08Z","timestamp":1782901568532,"version":"3.54.5"},"reference-count":44,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3053348","type":"journal-article","created":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T20:55:29Z","timestamp":1611262529000},"page":"17084-17099","source":"Crossref","is-referenced-by-count":74,"title":["A Multiagent Deep Reinforcement Learning Approach for Path Planning in Autonomous Surface Vehicles: The Ypacara\u00ed Lake Patrolling Case"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7796-3599","authenticated-orcid":false,"given":"Samuel Yanes","family":"Luis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel Gutierrez","family":"Reina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2612-0388","authenticated-orcid":false,"given":"Sergio L. Toral","family":"Marin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","volume":"4","author":"wang","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IAT.2004.1342959"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3349801.3349805"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1002\/9781118884614","volume":"9781118362","author":"schwartz","year":"2014","journal-title":"Multi-agent Machine Learning A Reinforcement Approach"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799442"},{"key":"ref37","author":"wooldridge","year":"2013","journal-title":"An Introduction to Multiagent Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2020.103078"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2918703"},{"key":"ref34","article-title":"UAV coverage path planning under varying power constraints using deep reinforcement learning","author":"theile","year":"2020","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2018.03.011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CcS49175.2020.9231484"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-0920-2"},{"key":"ref12","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":"ref13","first-page":"1","article-title":"Efficient collaborative multi-agent deep reinforcement learning for large-scale fleet management","author":"lin","year":"2018","journal-title":"Proc ACM SIGKDD Int Conf Knowledge Discovery and Data Mining"},{"key":"ref14","first-page":"1","article-title":"Off-policy multi-agent decomposed policy gradients","author":"wang","year":"2020","journal-title":"arXiv 2007 12322"},{"key":"ref15","first-page":"6380","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1879","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume":"3","author":"foerster","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953326"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943253"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2998015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3020067"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2017.7925381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.02.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2967225"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref5","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref8","author":"bellman","year":"1957","journal-title":"Dynamic Programming Rand Corporation Research Study"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-017-2895-x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref1","article-title":"Technical report: 12th sampling campaign from Ypakarai lake","author":"l\u00f3pez","year":"2016"},{"key":"ref20","first-page":"33","author":"fraga","year":"2014","journal-title":"Squirtle An ASV for Inland Water Environmental Monitoring"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s20051488"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1580-9_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2976586"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835397"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/483643"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3050934"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s19184055"},{"key":"ref43","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970433"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09330612.pdf?arnumber=9330612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T17:47:36Z","timestamp":1697651256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9330612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3053348","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}