{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:25:31Z","timestamp":1785248731500,"version":"3.55.0"},"reference-count":48,"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":"am","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\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1633363"],"award-info":[{"award-number":["IIS-1633363"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1836802"],"award-info":[{"award-number":["CNS-1836802"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1908308"],"award-info":[{"award-number":["CCF-1908308"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/tcomm.2020.3031930","type":"journal-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T17:41:30Z","timestamp":1603302090000},"page":"884-899","source":"Crossref","is-referenced-by-count":99,"title":["Experienced Deep Reinforcement Learning With Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0613-7334","authenticated-orcid":false,"given":"Ali Taleb Zadeh","family":"Kasgari","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-2458","authenticated-orcid":false,"given":"Walid","family":"Saad","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2556-115X","authenticated-orcid":false,"given":"Mohammad","family":"Mozaffari","sequence":"additional","affiliation":[{"name":"Ericsson Research, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800039"},{"key":"ref38","year":"2017","journal-title":"Technical Specification Group Services and System Aspects Service Requirements for the 5G System"},{"key":"ref33","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref30","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2043769"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014102"},{"key":"ref35","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 0255"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2018.8644250"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2957745"},{"key":"ref40","first-page":"1","article-title":"Convergence rates for the stochastic gradient descent method for non-convex objective functions","volume":"21","author":"fehrman","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2828407"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2874113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2013.02.017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2018.8417634"},{"key":"ref16","article-title":"Joint user association and resource allocation optimization for ultra reliable low latency HetNets","author":"yousefvand","year":"2018","journal-title":"arXiv 1809 06550"},{"key":"ref17","article-title":"Federated learning for ultra-reliable low-latency V2 V communications","author":"samarakoon","year":"2018","journal-title":"arXiv 1805 09253"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876548"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2930275"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013451"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680898"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2867029"},{"key":"ref6","first-page":"1","article-title":"Deep reinforcement learning for resource allocation in V2 V communications","author":"ye","year":"2018","journal-title":"Proc IEEE Int Conf Commun (ICC)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2850303"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569635"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879940"},{"key":"ref9","article-title":"Can terahertz provide high-rate reliable low latency communications for wireless VR?","author":"chaccour","year":"2020","journal-title":"arXiv 2005 00536"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761721"},{"key":"ref46","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486430"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref48","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7997286"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-95168-3_37"},{"key":"ref21","first-page":"47","article-title":"Deep reinforcement learning (DRL)-based resource management in software-defined and virtualized vehicular ad hoc networks","author":"he","year":"2018","journal-title":"Proc ACM Symp Develop Anal Intell Veh Netw Appl"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1900029"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2006.877962"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800635"},{"key":"ref26","article-title":"Risk-aware resource allocation for URLLC: Challenges and strategies with machine learning","author":"azari","year":"2018","journal-title":"arXiv 1901 04292"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154307"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227766"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/26\/9355073\/9229155-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/9355073\/09229155.pdf?arnumber=9229155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:48:48Z","timestamp":1652194128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9229155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2020.3031930","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}