{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T05:43:41Z","timestamp":1761198221167,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["IITP-2022-2018-0-01424","No. 2021-0-00892-002"],"award-info":[{"award-number":["IITP-2022-2018-0-01424","No. 2021-0-00892-002"]}],"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":[[2023]]},"DOI":"10.1109\/access.2023.3279401","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T17:45:18Z","timestamp":1684950318000},"page":"1-1","source":"Crossref","is-referenced-by-count":5,"title":["Multi-agent Reinforcement Learning-based Resource Allocation Scheme for UAV-assisted Internet of Remote Things Systems"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1869-6072","authenticated-orcid":false,"given":"Donggu","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, North Carolina State University, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7279-5090","authenticated-orcid":false,"given":"Young Ghyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electronic Convergence Engineering, Kwangwoon University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soo Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Convergence Engineering, Kwangwoon University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4716-6916","authenticated-orcid":false,"given":"Jae-Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Ajou University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4722-6387","authenticated-orcid":false,"given":"Yoan","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7711-8072","authenticated-orcid":false,"given":"Dong In","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-7097","authenticated-orcid":false,"given":"Jin Young","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Convergence Engineering, Kwangwoon University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/COMST.2021.3073036"},{"key":"ref35","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"},{"year":"2018","author":"sutton","journal-title":"Reinforcement Learning An Introduction","key":"ref12"},{"key":"ref34","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume":"80","author":"zhang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"arXiv 1911 10635"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/JIOT.2019.2962715"},{"key":"ref36","article-title":"An overview of gradient descent optimization algorithm","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/CTS.2012.6261045"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/LCOMM.2018.2822700"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/COMST.2019.2916583"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/TSP.2013.2241057"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/JPROC.2019.2957798"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/TSMCC.2007.913919"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/JIOT.2020.3021255"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref17","first-page":"2827","article-title":"Neural episodic control","volume":"70","author":"pritzel","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICCWorkshops53468.2022.9814506"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/JIOT.2022.3182119"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ACCESS.2021.3131714"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/TVT.2021.3128513"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TVT.2021.3071983"},{"key":"ref26","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1609\/aaai.v30i1.10295"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/JIOT.2020.3019186"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/LCOMM.2020.2978390"},{"key":"ref21","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"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TGRS.2021.3123109"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.23919\/JCC.2022.04.006"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/TCOMM.2016.2611512"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/TVT.2018.2865798"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TVT.2013.2272804"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/JIOT.2021.3089823"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ACCESS.2020.3033615"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1089\/space.2017.0032"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/COMST.2003.5342227"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/COMST.2020.2964534"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/6514899\/10132480.pdf?arnumber=10132480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T01:01:41Z","timestamp":1686099701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3279401","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}