{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T01:38:57Z","timestamp":1780709937438,"version":"3.54.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Science and Technology Plan Project of Guangdong Province","award":["2020A050515010"],"award-info":[{"award-number":["2020A050515010"]}]},{"name":"Science and Technology Plan Project of Guangdong Province","award":["2021A0505030015"],"award-info":[{"award-number":["2021A0505030015"]}]},{"name":"Special Support Plan for High-Level Talents of Guangdong Province","award":["2019TQ05X409"],"award-info":[{"award-number":["2019TQ05X409"]}]},{"name":"Open Research Project Programme of the State Key Laboratory of Internet of Things for Smart City","award":["SKL-IoTSC(UM)-2021-2023\/ORPF\/A04\/2022"],"award-info":[{"award-number":["SKL-IoTSC(UM)-2021-2023\/ORPF\/A04\/2022"]}]},{"name":"Open Research Fund of ISN Laboratory","award":["ISN23-12"],"award-info":[{"award-number":["ISN23-12"]}]},{"DOI":"10.13039\/501100006469","name":"FDCT","doi-asserted-by":"publisher","award":["0119\/2020\/A3"],"award-info":[{"award-number":["0119\/2020\/A3"]}],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006469","name":"FDCT","doi-asserted-by":"publisher","award":["SKL-IOTSC(UM)-2021-2023"],"award-info":[{"award-number":["SKL-IOTSC(UM)-2021-2023"]}],"id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GDST","award":["2021A1515011900"],"award-info":[{"award-number":["2021A1515011900"]}]},{"name":"GDST","award":["2020B1212030003"],"award-info":[{"award-number":["2020B1212030003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171461"],"award-info":[{"award-number":["62171461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu","award":["BK20212001"],"award-info":[{"award-number":["BK20212001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tcomm.2022.3171837","type":"journal-article","created":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T20:18:27Z","timestamp":1651522707000},"page":"3849-3864","source":"Crossref","is-referenced-by-count":64,"title":["Deep Reinforcement Learning-Based Optimization for IRS-Assisted Cognitive Radio Systems"],"prefix":"10.1109","volume":"70","author":[{"given":"Canwei","family":"Zhong","sequence":"first","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5947-7036","authenticated-orcid":false,"given":"Miao","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8292-401X","authenticated-orcid":false,"given":"Guangchi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0043-3266","authenticated-orcid":false,"given":"Qingqing","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9294-664X","authenticated-orcid":false,"given":"Xinrong","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Communications Engineering, Army Engineering University of PLA, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1863-6149","authenticated-orcid":false,"given":"Xiaoli","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Electronic and Electrical Engineering, The University of Sheffield, Sheffield, U.K"}],"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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2093210"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/98.788210"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2158673"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3113995"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2004.839380"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2936025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3051897"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.2979709"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3011308"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3033006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2919685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3087495"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2961357"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2986438"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3008402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2923997"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2958916"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.2969167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000835"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2022.3165590"},{"key":"ref25","article-title":"A reinforcement learning approach for an IRS-assisted NOMA network","author":"Xie","year":"2021","journal-title":"arXiv:2106.09611"},{"key":"ref26","article-title":"Reinforcement learning with deep energy-based policies","author":"Haarnoja","year":"2017","journal-title":"arXiv:1702.08165"},{"key":"ref27","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018","journal-title":"arXiv:1812.05905"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.02.080476"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2280655"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322372"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154301"},{"key":"ref32","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref34","volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"Ziebart","year":"2010"},{"key":"ref35","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"arXiv:1802.09477"},{"key":"ref36","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/9796992\/09766179.pdf?arnumber=9766179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:59:06Z","timestamp":1705960746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9766179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":36,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2022.3171837","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}