{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T03:40:15Z","timestamp":1785814815516,"version":"3.56.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1731017"],"award-info":[{"award-number":["1731017"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1815637"],"award-info":[{"award-number":["1815637"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/jsac.2019.2933962","type":"journal-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T19:44:00Z","timestamp":1565293440000},"page":"2282-2292","source":"Crossref","is-referenced-by-count":533,"title":["Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8489-1933","authenticated-orcid":false,"given":"Le","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1544-1768","authenticated-orcid":false,"given":"Hao","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey Ye","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref32","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"tan","year":"1993","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref31","article-title":"Deep reinforcement learning for distributed dynamic power allocation in wireless networks","author":"nasir","year":"2018","journal-title":"arXiv 1808 00490"},{"key":"ref30","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref37","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"key":"ref36","year":"2007","journal-title":"WINNER II Channel Models"},{"key":"ref35","year":"2016","journal-title":"WF on SLS Evaluation Assumptions for eV2X"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1700274"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2014.6952482"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2479248"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2509978"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876548"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699194"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2702747"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2827958"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2014.6884222"},{"key":"ref4","year":"2017","journal-title":"Technical Specification Group Radio Access Network Study Enhancement 3GPP Support for 5G V2X Services (Release 15)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2709462"},{"key":"ref3","year":"2016","journal-title":"Technical Specification Group Radio Access Network Study LTE-Based V2X Services (Release 14)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref29","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2017.2752798"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2833427"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2751641"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2750903"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2018.2811185"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.7553036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872122"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2538461"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2017.7959912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2622180"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/49\/8839628\/8792382-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/8839628\/08792382.pdf?arnumber=8792382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:06Z","timestamp":1649443686000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8792382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":37,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2019.2933962","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}