{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:43:31Z","timestamp":1775814211883,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N029720\/2"],"award-info":[{"award-number":["EP\/N029720\/2"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/twc.2019.2935201","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T15:39:35Z","timestamp":1566488375000},"page":"729-743","source":"Crossref","is-referenced-by-count":503,"title":["Multi-Agent Reinforcement Learning-Based Resource Allocation for UAV Networks"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8850-358X","authenticated-orcid":false,"given":"Jingjing","family":"Cui","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6389-8941","authenticated-orcid":false,"given":"Yuanwei","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8337-5884","authenticated-orcid":false,"given":"Arumugam","family":"Nallanathan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"osborne","year":"1994","journal-title":"A Course in Game Theory"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2514\/6.2004-6490"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-010-0189-2_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2867180"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2011.159"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2334673"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043124"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2009.5346172"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2593468"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2013.192"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8756984"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WOWMOM.2008.4594888"},{"key":"ref22","article-title":"Cellular-connected UAVs over 5G: Deep reinforcement learning for interference management","author":"challita","year":"2018","journal-title":"arXiv 1801 05500"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2811372"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254746"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2012.2211905"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM.2013.160"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2578312"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2700840"},{"key":"ref40","article-title":"From single-agent to multi-agent reinforcement learning: Foundational concepts and methods","author":"neto","year":"2005","journal-title":"Learning theory course"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2633248"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2857211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2611512"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2790401"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2789293"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2892131"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2514\/6.2009-54"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160554"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7470932"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7470937"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.2006127"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2342736"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864423"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref49","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2015.7417609"},{"key":"ref46","article-title":"Complexity analysis of real-time reinforcement learning applied to finding shortest paths in deterministic domains","author":"koenig","year":"1992"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2307\/2312726"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329434"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.037"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref44","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc 15th National\/Tenth Conf Artif Intell \/Innov Appl Artif Intell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2815628"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/8994112\/08807386.pdf?arnumber=8807386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:36:41Z","timestamp":1641987401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8807386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/twc.2019.2935201","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}