{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:37:52Z","timestamp":1793320672720,"version":"4.5.0"},"reference-count":42,"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":"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571062"],"award-info":[{"award-number":["61571062"]}],"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":["61871047"],"award-info":[{"award-number":["61871047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4202049"],"award-info":[{"award-number":["4202049"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2018YFB1800805"],"award-info":[{"award-number":["2018YFB1800805"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/tvt.2019.2961405","type":"journal-article","created":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T05:02:29Z","timestamp":1577163749000},"page":"1828-1840","source":"Crossref","is-referenced-by-count":147,"title":["Multi-Agent Deep Reinforcement Learning Based Spectrum Allocation for D2D Underlay Communications"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2535-2523","authenticated-orcid":false,"given":"Zheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8892-4520","authenticated-orcid":false,"given":"Caili","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CAMAD.2018.8514983"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISPACS.2016.7824674"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2922668"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2838574"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1515\/9781400829460"},{"key":"ref36","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1976.29"},{"key":"ref34","article-title":"A multi-agent deep reinforcement learning based spectrum allocation framework for D2D underlay communications","author":"li","year":"0","journal-title":"Proc IEEE Global Telecomm Con (GLOBECOM"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2251604"},{"key":"ref40","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2553124"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/NRSC.2017.7893487"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2015.2498925"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2017.2771778"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1500356WC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2467174"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.022014.130840"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1204","DOI":"10.1109\/TMC.2017.2744620","article-title":"Intelligent spectrum management based on transfer actor-critic learning for rateless transmissions in cognitive radio networks","volume":"17","author":"hu","year":"2018","journal-title":"IEEE Trans Mobile Comput"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1800085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2013.6590055"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2011.122010.100963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422778"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2883669"},{"key":"ref5","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2842738"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2018.8580784"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.071013.120787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1999.780118"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2880956"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP.2014.7073432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890686"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2890210"},{"key":"ref42","first-page":"2v","article-title":"Further advancements for e-utra physical layer aspects","volume":"36","author":"access","year":"2010","journal-title":"3GPP Technical Specification"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2018.8450518"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"529?533","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422586"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2593468"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/8995806\/08938826.pdf?arnumber=8938826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:45:45Z","timestamp":1651067145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8938826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":42,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2019.2961405","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2]]}}}