{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:24:35Z","timestamp":1770747875938,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/twc.2020.3024166","type":"journal-article","created":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T23:57:02Z","timestamp":1600819022000},"page":"228-242","source":"Crossref","is-referenced-by-count":19,"title":["Throughput Optimization for Grant-Free Multiple Access With Multiagent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2745-1197","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3821-4365","authenticated-orcid":false,"given":"Vincent W.S.","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Schober","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Age of information in ultra-dense IoT systems: Performance and mean-field game analysis","author":"zhou","year":"2020","journal-title":"arXiv 2006 15756"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2953132"},{"key":"ref33","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-35289-8_25","article-title":"Stochastic gradient descent tricks","author":"bottou","year":"2012","journal-title":"Neural Networks Tricks Trade"},{"key":"ref31","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"},{"key":"ref30","first-page":"1","article-title":"Friend-or-foe Q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref37","first-page":"1239","article-title":"Incorporating functional knowledge in neural networks","volume":"10","author":"dugas","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref36","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv 1803 00933"},{"key":"ref35","author":"weiss","year":"2013","journal-title":"Multiagent Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8909-3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2017.8170921"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422634"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","author":"kapturowski","year":"2019","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2014.2302471"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2360821"},{"key":"ref16","first-page":"155","article-title":"Multi-player bandits: A musical chairs approach","author":"rosenski","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref17","first-page":"1","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref18","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc 4th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref19","first-page":"1","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref28","year":"2019","journal-title":"Technical Specification Group Services and System Aspects System Architecture for the 5G System (5GS) Stage 2 (Release 16)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2844341"},{"key":"ref27","year":"2020","journal-title":"Technical Specification Group Radio Access Network NR Physical layer procedures for data (Release 15)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2017.2649104"},{"key":"ref6","year":"2019","journal-title":"Technical Specification Group Radio Access Network NR Physical Layer Procedures for Control (Release 15)"},{"key":"ref29","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref5","year":"2020","journal-title":"Cisco Annual Internet Report (2018–2023)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2687218"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/9781316771655"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2803740"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996393"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013451"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2200\/S00271ED1V01Y201006CNT007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015410"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2907853"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2527601"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/9319597\/09204466.pdf?arnumber=9204466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:04Z","timestamp":1652194324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9204466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":39,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/twc.2020.3024166","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}