{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:28:51Z","timestamp":1772908131954,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001103"],"award-info":[{"award-number":["62001103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61720106003"],"award-info":[{"award-number":["61720106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018YFB1800801"],"award-info":[{"award-number":["2018YFB1800801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tvt.2021.3055511","type":"journal-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T21:03:18Z","timestamp":1611954198000},"page":"1658-1672","source":"Crossref","is-referenced-by-count":50,"title":["Multi-Agent Reinforcement Learning Based Distributed Transmission in Collaborative Cloud-Edge Systems"],"prefix":"10.1109","volume":"70","author":[{"given":"Chunmei","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6579-9798","authenticated-orcid":false,"given":"Shengheng","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2663-4207","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-4616","authenticated-orcid":false,"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zhaohua","family":"Lu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1806","authenticated-orcid":false,"given":"Luxi","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VETECF.2009.5379009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.855401"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2549418"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.011714.130846"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6736750"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2895792"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2005.862421"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.879269"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7010533"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2520912"},{"key":"ref28","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc 31st Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2013.2260813"},{"key":"ref2","article-title":"Cisco visual networking index: Global mobile data traffic forecast update 2017–2022","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SAM48682.2020.9104386"},{"key":"ref20","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref21","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"15","DOI":"10.23919\/JCIN.2019.8917869","article-title":"An overview of intelligent wireless communications using deep reinforcement learning","volume":"4","author":"huang","year":"2019","journal-title":"J Commun Inf Netw"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422864"},{"key":"ref25","author":"weiss","year":"1999","journal-title":"Multiagent Systems A Modern Approach to Distributed Artificial Intelligence"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref51","first-page":"1","article-title":"Reward constrained policy optimization","author":"tessler","year":"0","journal-title":"Proc Int Conf Learn Represent (ICLR'19)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2016.7794819"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248563"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2006.255506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2744648"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2799138"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2413394"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2545539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699958"},{"key":"ref18","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref19","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6898939"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2571730"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6871674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1700007"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.7721750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2771153"},{"key":"ref49","author":"puterman","year":"2009","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900317"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761075"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2789895"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2200\/S00271ED1V01Y201006CNT007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328154"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.052313.121128"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2479226"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2687078"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2745570"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9374720\/09340599.pdf?arnumber=9340599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:31:53Z","timestamp":1670977913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2021.3055511","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}