{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:00:14Z","timestamp":1764842414323,"version":"3.37.3"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB1800800\/802"],"award-info":[{"award-number":["2018YFB1800800\/802"]}]},{"DOI":"10.13039\/501100015956","name":"Special Project for Research and Development in Key areas of Guangdong Province","doi-asserted-by":"publisher","award":["2018B030338001"],"award-info":[{"award-number":["2018B030338001"]}],"id":[{"id":"10.13039\/501100015956","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC-61629101","NSFC- 61771066"],"award-info":[{"award-number":["NSFC-61629101","NSFC- 61771066"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Research Project","award":["2017ZT07X152"],"award-info":[{"award-number":["2017ZT07X152"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2021,2,15]]},"DOI":"10.1109\/jiot.2020.3021017","type":"journal-article","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T20:58:15Z","timestamp":1598993895000},"page":"2681-2693","source":"Crossref","is-referenced-by-count":9,"title":["Voting-Based Multiagent Reinforcement Learning for Intelligent IoT"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-4357","authenticated-orcid":false,"given":"Yue","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zengde","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2101-9507","authenticated-orcid":false,"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8767-4742","authenticated-orcid":false,"given":"Wenjun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2588-7851","authenticated-orcid":false,"given":"Anthony Man-Cho","family":"So","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Primal-dual $\\pi$ learning Sample complexity and sublinear run time for ergodic Markov decision problems","year":"2017","author":"wang","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.05.002"},{"key":"ref33","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","article-title":"Game theory-based control system algorithms with real-time reinforcement learning: How to solve multiplayer games online","volume":"37","author":"vamvoudakis","year":"2017","journal-title":"IEEE Control Syst Mag"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2598476"},{"key":"ref34","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7510820"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1002\/wcm.72","article-title":"A survey of mobility models for ad hoc network research","volume":"2","author":"lyu","year":"2002","journal-title":"Wireless Commun Mobile Comput"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WCNCW.2015.7122576"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2900035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2585302"},{"key":"ref27","first-page":"2629","article-title":"Deep-reinforcement learning multiple access for heterogeneous wireless networks","volume":"8","author":"ghavamzadeh","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872440"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2368731"},{"key":"ref21","first-page":"9340","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619839"},{"key":"ref23","first-page":"9649","article-title":"Multi-agent reinforcement learning via double averaging primal–dual optimization","author":"wai","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref26","first-page":"2258","article-title":"Efficient average reward reinforcement learning using constant shifting values","author":"yang","year":"2016","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-70087-8_79"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref51","first-page":"996","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","author":"kearns","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2700840"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8423028"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680898"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2633248"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref54","first-page":"494","article-title":"Investigating practical linear temporal difference learning","author":"adam","year":"2016","journal-title":"Proc Int'l Joint Conf Autonomous Agents and Multiagent Systems (AAMAS)"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2005","author":"bertsekas","key":"ref53"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2906789"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref40","first-page":"834","article-title":"Scalable bilinear ? learning using state and action features","author":"chen","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2780087"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2894403"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref16","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref18","first-page":"6379","article-title":"Multi-agent actor–critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref19","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2935010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2962715"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2935450"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5368-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377340"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2007.15"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2007.900165"},{"key":"ref48","first-page":"3877","article-title":"PAC optimal MDP planning with application to invasive species management","volume":"16","author":"taleghan","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref47","first-page":"1","article-title":"PAC optimal planning for invasive species management: Improved exploration for reinforcement learning from simulator-defined MDPs","author":"dietterich","year":"2013","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref42","first-page":"1049","article-title":"Stochastic variance reduction methods for policy evaluation","author":"du","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref41","first-page":"1458","article-title":"Learning from conditional distributions via dual embeddings","author":"dai","year":"2017","journal-title":"Proc Artif Intell Stat (AISTATS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2016.2641219"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2626274"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9348955\/09184075.pdf?arnumber=9184075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:44Z","timestamp":1652194424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9184075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,15]]},"references-count":63,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.3021017","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2021,2,15]]}}}