{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:32:29Z","timestamp":1778347949608,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"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":["61976113"],"award-info":[{"award-number":["61976113"]}],"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":["U1936201"],"award-info":[{"award-number":["U1936201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018YFB1801105"],"award-info":[{"award-number":["2018YFB1801105"]}]},{"name":"Key Areas of Research, and Development Program of Guangdong Province","award":["2018B010114001"],"award-info":[{"award-number":["2018B010114001"]}]},{"name":"Central Universities","award":["ZYGX2019Z022"],"award-info":[{"award-number":["ZYGX2019Z022"]}]},{"name":"Introducing Talents of Discipline to Universities","award":["B20064"],"award-info":[{"award-number":["B20064"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/tvt.2020.3020400","type":"journal-article","created":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T20:30:04Z","timestamp":1599078604000},"page":"13124-13138","source":"Crossref","is-referenced-by-count":186,"title":["Joint Optimization of Handover Control and Power Allocation Based on Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8725-6804","authenticated-orcid":false,"given":"Delin","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1646-8455","authenticated-orcid":false,"given":"Lan","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4181-580X","authenticated-orcid":false,"given":"Xinggan","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2671-5090","authenticated-orcid":false,"given":"Ying-Chang","family":"Liang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Asymptopia: An exposition of statistical asymptotic theory","author":"pollard","year":"2009"},{"key":"ref38","author":"levin","year":"2009","journal-title":"Markov Chains and Mixing Times"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref32","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2016.2551042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2582152"},{"key":"ref37","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref36","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/wcm.72"},{"key":"ref34","article-title":"Openai baselines","author":"dhariwal","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2015.7127696"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2762668"},{"key":"ref14","article-title":"Parallel contextual bandits in wireless handover optimization","author":"colin","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5GWF49715.2020.9221072"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2612038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2877326"},{"key":"ref18","first-page":"692","article-title":"Reinforcement learning based predictive handover for pedestrian-aware mmwave","author":"yusuke","year":"0","journal-title":"Proc IEEE Conf Comput Commun Workshops"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2961655"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Comput Sci"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2017.7925950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","article-title":"Protocal Specification: Evolved Universal Terrestrial Radio Access (E-UTRA); Radio Resource Control (RRC)","year":"2013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14257\/ijca.2014.7.4.04"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM.2012.6290250"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAIE.2015.7298317"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICECC.2011.6067552"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.10.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2011.101310.00005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2015.7341220"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.2328098"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2848295"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref23","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"lowe","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref26","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref25","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9258483\/09185035.pdf?arnumber=9185035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:45:04Z","timestamp":1651067104000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9185035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":39,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2020.3020400","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11]]}}}