{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:44:46Z","timestamp":1774968286631,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1731017"],"award-info":[{"award-number":["1731017"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1815637"],"award-info":[{"award-number":["1815637"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/jproc.2019.2957798","type":"journal-article","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T20:46:50Z","timestamp":1577479610000},"page":"341-356","source":"Crossref","is-referenced-by-count":239,"title":["Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks"],"prefix":"10.1109","volume":"108","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8489-1933","authenticated-orcid":false,"given":"Le","family":"Liang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1544-1768","authenticated-orcid":false,"given":"Hao","family":"Ye","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1354-2557","authenticated-orcid":false,"given":"Guanding","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Geoffrey Ye","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422168"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646405"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2025561"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/T-WC.2008.071349"},{"key":"ref76","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2431121"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2953724"},{"key":"ref75","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2947591"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2010.01.091494"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2284494"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2827958"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699194"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2017.2752798"},{"key":"ref30","year":"2016","journal-title":"3rd generation partnership project technical specification group radio access network study on lte-based v2x services (release 14)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2016.9"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2509978"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2479248"},{"key":"ref60","article-title":"Towards optimal power control via ensembling deep neural networks","author":"liang","year":"2018","journal-title":"arXiv 1807 10025"},{"key":"ref62","first-page":"2908","article-title":"Deep linear networks with arbitrary loss: All local minima are global","author":"laurent","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2908906"},{"key":"ref63","article-title":"Gradient descent finds global minima of deep neural networks","author":"du","year":"2018","journal-title":"arXiv 1811 03804"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872122"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2811185"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933893"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2926625"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2829773"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902372"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511619748"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2825444"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2921627"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2924010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933969"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800601"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.01.090031"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2538461"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2949589"},{"key":"ref93","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref92","article-title":"Optimal wireless resource allocation with random edge graph neural networks","author":"eisen","year":"2019","journal-title":"arXiv 1909 01865"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815526"},{"key":"ref90","article-title":"Learn to compress CSI and allocate resources in vehicular networks","author":"wang","year":"2019","journal-title":"arXiv 1908 04685"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006944"},{"key":"ref58","article-title":"Graph embedding based wireless link scheduling with few training samples","author":"lee","year":"2019","journal-title":"arXiv 1906 02871"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904352"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647453"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The Hungarian method for the assignment problem","volume":"2","author":"kuhn","year":"1995","journal-title":"Naval Res Logist"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2843359"},{"key":"ref53","article-title":"A globally optimal energy-efficient power control framework and its efficient implementation in wireless interference networks","author":"matthiesen","year":"2018","journal-title":"arXiv 1812 06920"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2758370"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2784180"},{"key":"ref40","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2757490"},{"key":"ref13","article-title":"Deep learning based end-to-end wireless communication systems with conditional GAN as unknown channel","author":"ye","year":"2019","journal-title":"arXiv 1903 02551"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2899805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2868322"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997440"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2866382"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1700317"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2812733"},{"key":"ref89","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/49.793310"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2006.877962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2004.843065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2005.1561930"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/JSTSP.2007.914876","article-title":"Dynamic spectrum management: Complexity and duality","volume":"2","author":"luo","year":"2008","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2004.843067"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2050062"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2016.7848885"},{"key":"ref88","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2867029"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref48","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref47","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref41","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000071"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5\/8967317\/8943940-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/8967317\/08943940.pdf?arnumber=8943940","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:40:23Z","timestamp":1651066823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8943940\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":94,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2019.2957798","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}