{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:48:18Z","timestamp":1777891698114,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"publisher","award":["W911NF1910221"],"award-info":[{"award-number":["W911NF1910221"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"publisher","award":["NSF-CNS-2147955"],"award-info":[{"award-number":["NSF-CNS-2147955"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"publisher","award":["NSF-CCF-2225555"],"award-info":[{"award-number":["NSF-CCF-2225555"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/twc.2022.3215922","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:24:15Z","timestamp":1667517855000},"page":"3038-3054","source":"Crossref","is-referenced-by-count":16,"title":["Reinforcement Learning-Based Joint User Scheduling and Link Configuration in Millimeter-Wave Networks"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0136-8053","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4666-5628","authenticated-orcid":false,"given":"Robert W.","family":"Heath","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2772251"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241556"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467044"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144107"},{"key":"ref53","first-page":"2249","article-title":"An empirical evaluation of Thompson sampling","author":"chapelle","year":"2011","journal-title":"Proc 24th Int Conf Neural Inf Process Syst"},{"key":"ref52","article-title":"On improving deep reinforcement learning for POMDPs","author":"zhu","year":"2017","journal-title":"arXiv 1704 07978"},{"key":"ref11","first-page":"1","year":"2019","journal-title":"System Architecture for the 5G System"},{"key":"ref55","author":"zhang","year":"2021","journal-title":"Source Code for Paper Titled Reinforcement Learning-Based Joint User Scheduling and Link Configuration in Millimeter-Wave Networks"},{"key":"ref10","first-page":"1","year":"2019","journal-title":"IEEE Draft Standard for Information Technology–Telecommunications and Information Exchange Between Systems Local and Metropolitan Area Networks–Specific Requirements—Part 11 Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications–Amendment Enhanced Throughput for Operation in License-Exempt Bands Above 45 GHz"},{"key":"ref54","author":"maltsev","year":"2014","journal-title":"WP5 Propagation antenna and multi-antenna techniques D5 1—Channel modeling and characterization"},{"key":"ref17","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419208"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2903655"},{"key":"ref51","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref50","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2619705"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144146"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2007.94"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3323679.3326532"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3005138"},{"key":"ref41","article-title":"Neural networks based beam codebooks: Learning mmWave massive MIMO beams that adapt to deployment and hardware","author":"alrabeiah","year":"2020","journal-title":"arXiv 2006 14501"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3033514"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8056991"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2017.7959894"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2322660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2552239"},{"key":"ref9","year":"0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MASS.2017.48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155408"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1601120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3046501"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155475"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248501"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2947925"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2922064"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2947923"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2972614"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3018955"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2958814"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2950274"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2015.7010533"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2013.2260813"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3047547"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2772881"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC48278.2020.9217110"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2026943"},{"key":"ref26","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/18.212277"},{"key":"ref21","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322560"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647289"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014270"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7693\/10122187\/9930939-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10122187\/09930939.pdf?arnumber=9930939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:27:32Z","timestamp":1686594452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9930939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":55,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3215922","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}