{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:15:52Z","timestamp":1780053352474,"version":"3.54.0"},"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701230"],"award-info":[{"award-number":["61701230"]}],"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":["62071230"],"award-info":[{"award-number":["62071230"]}],"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":["62002166"],"award-info":[{"award-number":["62002166"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20170805"],"award-info":[{"award-number":["BK20170805"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M671483"],"award-info":[{"award-number":["2020M671483"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1109\/twc.2020.3031436","type":"journal-article","created":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T19:49:05Z","timestamp":1603396145000},"page":"1175-1187","source":"Crossref","is-referenced-by-count":95,"title":["Energy-Efficient Mode Selection and Resource Allocation for D2D-Enabled Heterogeneous Networks: A Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-788X","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6784-5583","authenticated-orcid":false,"given":"Kun","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhua","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref38","first-page":"262","article-title":"Analysis and improvement of policy gradient estimation","author":"zhao","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2015.7248660"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2010.5506248"},{"key":"ref37","first-page":"2775","article-title":"Bridging the gap between value and policy based reinforcement learning","author":"nachum","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.06.016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2944403"},{"key":"ref40","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2311580"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2362005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/fi10010003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403676"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2018.8690728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885887"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2956111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2019.0466"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-020-02261-y"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2933417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2916352"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2769644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2917907"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2018.8450467"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2580153"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2871073"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2916395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11235-017-0320-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2907252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSPA.2019.8713700"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2731798"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-49430-8_2","article-title":"Efficient backprop","author":"lecun","year":"1998","journal-title":"Neural Networks Tricks of the Trade"},{"key":"ref20","first-page":"123","article-title":"SWIPT techniques in multi-tier D2D networks for energy efficiency","year":"2019","journal-title":"Proc TENCON - IEEE Region 10 Conf (TENCON)"},{"key":"ref45","year":"2010","journal-title":"Evolved Universal Terrestrial Radio Access (E-UTRA) Further advancements for E-UTRA physical layer aspects"},{"key":"ref48","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2015","journal-title":"arXiv 1511 06581"},{"key":"ref22","first-page":"146","article-title":"A reinforcement learning based joint spectrum allocation and power control algorithm for D2D communication underlaying cellular networks","author":"chen","year":"2019","journal-title":"Proc Int Conf Artif Intell Commun Netw"},{"key":"ref47","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artificial Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2018.8650160"},{"key":"ref41","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2018.6028"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2015.7343537"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2018.2844301"},{"key":"ref43","year":"2014","journal-title":"Study on LTE Device to Device Proximity Services Radio Aspects"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2017.8292468"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/9352576\/09237143.pdf?arnumber=9237143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T19:39:06Z","timestamp":1643830746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9237143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/twc.2020.3031436","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}