{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:48:38Z","timestamp":1781974118615,"version":"3.54.5"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Education-China Mobile Communications Group Co., Ltd (MoE-CMCC) Artificial Intelligence Project","award":["MCM20190701"],"award-info":[{"award-number":["MCM20190701"]}]},{"DOI":"10.13039\/501100002766","name":"Beijing University of Posts and Telecommunications Excellent Ph.D. Students Foundation","doi-asserted-by":"publisher","award":["CX2021112"],"award-info":[{"award-number":["CX2021112"]}],"id":[{"id":"10.13039\/501100002766","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/twc.2022.3233853","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:10:29Z","timestamp":1673377829000},"page":"5414-5430","source":"Crossref","is-referenced-by-count":48,"title":["Multi-Agent Deep Reinforcement Learning Based Resource Allocation for Ultra-Reliable Low-Latency Internet of Controllable Things"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6897-5531","authenticated-orcid":false,"given":"Yang","family":"Xiao","sequence":"first","affiliation":[{"name":"Intelligent Perception and Computing Research Center, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8495-3487","authenticated-orcid":false,"given":"Yuqian","family":"Song","sequence":"additional","affiliation":[{"name":"Intelligent Perception and Computing Research Center, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4007-6109","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Intelligent Perception and Computing Research Center, School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2935545"},{"key":"ref35","article-title":"A review of cooperative multi-agent deep reinforcement learning","author":"oroojlooyjadid","year":"2019","journal-title":"arXiv 1908 03963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838659"},{"key":"ref37","first-page":"780","article-title":"Predicting and preventing coordination problems in cooperative Q-learning systems","author":"fulda","year":"2007","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685145"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S1570-7946(05)80133-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0098-1354(95)87027-X"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00138689"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3032991"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(01)00732-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/26.935159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3096928"},{"key":"ref38","first-page":"11987","article-title":"Learning in two-player zero-sum partially observable Markov games with perfect recall","volume":"34","author":"kozuno","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871595"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2099222"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2771534"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref23","year":"2022","journal-title":"Study on Scenarios and Requirements for Next Generation Access Technologies (Release 16)"},{"key":"ref45","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2009.5449938"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2490540"},{"key":"ref47","first-page":"105","article-title":"Convergence proof for actor-critic methods applied to PPO and RUDDER","author":"holzleitner","year":"2021","journal-title":"Transactions on Large-Scale Data- and Knowledge-Centered Systems I"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2016.7504435"},{"key":"ref42","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"arXiv 1706 05296"},{"key":"ref41","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2867029"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2812733"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5783982"},{"key":"ref43","article-title":"Implementation matters in deep policy gradients: A case study on PPO and TRPO","author":"engstrom","year":"2020","journal-title":"arXiv 2005 12729"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.sorms.2012.08.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2773572"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0098-1354(92)80028-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3069240"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3089823"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3144726"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3102580"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04301-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2980586"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023111"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10214970\/10014697.pdf?arnumber=10014697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:12:04Z","timestamp":1693246324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10014697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":47,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3233853","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}