{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:04:17Z","timestamp":1772550257001,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001807","name":"Fundao de Amparo Pesquisa do Estado de So Paulo","doi-asserted-by":"publisher","award":["2017\/50361-0"],"award-info":[{"award-number":["2017\/50361-0"]}],"id":[{"id":"10.13039\/501100001807","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-11-LABX-0031-01"],"award-info":[{"award-number":["ANR-11-LABX-0031-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DrIVE","award":["EQA-041801"],"award-info":[{"award-number":["EQA-041801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tnsm.2021.3122505","type":"journal-article","created":{"date-parts":[[2021,10,25]],"date-time":"2021-10-25T19:44:22Z","timestamp":1635191062000},"page":"4063-4074","source":"Crossref","is-referenced-by-count":29,"title":["Harnessing UAVs for Fair 5G Bandwidth Allocation in Vehicular Communication via Deep Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6685-9553","authenticated-orcid":false,"given":"Tingting","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3109-4305","authenticated-orcid":false,"given":"Christian Esteve","family":"Rothenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9720-1690","authenticated-orcid":false,"given":"Katia","family":"Obraczka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2044-1279","authenticated-orcid":false,"given":"Chadi","family":"Barakat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0089-6340","authenticated-orcid":false,"given":"Thierry","family":"Turletti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref32","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"arXiv 1804 08617"},{"key":"ref31","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2018.8624183"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref34","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864373"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/90.879343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2927425"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875493"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2633248"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2943147"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2578312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/s19235170"},{"key":"ref28","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"Proc Conf Neural Inf Process Syst (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2017.2734243"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","article-title":"Tutorial on UAV: A blue sky view on wireless communication","author":"vinogradov","year":"2019","journal-title":"arXiv 1901 02306"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377340"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2906228"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2948324"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2952892"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2752161"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2495297"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1002\/ett.4427","article-title":"Machine learning for next-generation intelligent transportation systems: A survey","author":"yuan","year":"2022","journal-title":"Trans Emerging Telecomm Technol (ETT)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680898"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2991326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2342736"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref26","author":"dias","year":"2018","journal-title":"CRAWDAD Dataset Coppe-Ufrj\/RioBuses (V 2018-03-19)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2902559"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4275028\/9644641\/09585312.pdf?arnumber=9585312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T20:06:32Z","timestamp":1673640392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":36,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2021.3122505","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}