{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:22:35Z","timestamp":1785511355311,"version":"3.56.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European H2020 Project HEIMDALL","award":["740689"],"award-info":[{"award-number":["740689"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2021.3055651","type":"journal-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T15:56:26Z","timestamp":1611935786000},"page":"123269-123281","source":"Crossref","is-referenced-by-count":29,"title":["Wildfire Front Monitoring With Multiple UAVs Using Deep Q-Learning"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5219-6533","authenticated-orcid":false,"given":"Alberto","family":"Viseras","sequence":"first","affiliation":[{"name":"Institute of Communications and Navigation, German Aerospace Center (DLR), Oberpfaffenhofen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7092-7520","authenticated-orcid":false,"given":"Michael","family":"Meissner","sequence":"additional","affiliation":[{"name":"Institute of Communications and Navigation, German Aerospace Center (DLR), Oberpfaffenhofen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Marchal","sequence":"additional","affiliation":[{"name":"Institute of Communications and Navigation, German Aerospace Center (DLR), Oberpfaffenhofen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1890\/10-2213.1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1139\/cjfr-2014-0347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISASS.2019.8757707"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593539"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/oca.2424"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOMW.2019.8845309"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34094-0_10"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2857475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2514\/1.G004106"},{"key":"ref12","first-page":"195","article-title":"Planning, learning and coordination in multiagent decision processes","volume-title":"Proc. 6th Conf. Theor. Aspects Rationality Knowledge","author":"Boutilier"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref14","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11676-015-0088-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS.2015.7274615"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8127673"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2016.05.007"},{"key":"ref19","first-page":"1","article-title":"A survey of unmanned aerial vehicle (UAV) usage for imagery collection in disaster research and management","volume-title":"Proc. 9th Int. Workshop Remote Sens. Disaster Response","volume":"8","author":"Adams"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5194\/nhess-18-1079-2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11676-016-0361-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s16081310"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1071\/WF14176"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73958-6_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1470520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2007.4434345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2514\/1.48403"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20108"},{"key":"ref29","article-title":"Cooperative and distributed reinforcement learning of drones for field coverage","author":"Xuan Pham","year":"2018","journal-title":"arXiv:1803.07250"},{"key":"ref30","article-title":"Learning multi-robot decentralized Macro-Action-Based policies via a centralized Q-Net","author":"Xiao","year":"2019","journal-title":"arXiv:1909.08776"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2924839"},{"key":"ref32","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Foerster"},{"key":"ref33","article-title":"Emergent tool use from multi-agent autocurricula","author":"Baker","year":"2019","journal-title":"arXiv:1909.07528"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref35","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref37","article-title":"Deep reinforcement learning","author":"Li","year":"2018","journal-title":"arXiv:1810.06339"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref39","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018","journal-title":"arXiv:1803.11485"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref45","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"Kok","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2019.8848961"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10820123\/09340340.pdf?arnumber=9340340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T06:28:47Z","timestamp":1753511327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3055651","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}