{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T03:35:12Z","timestamp":1775446512945,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":["62131005"],"award-info":[{"award-number":["62131005"]}],"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":["U19B2014"],"award-info":[{"award-number":["U19B2014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["254"],"award-info":[{"award-number":["254"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2022,11]]},"DOI":"10.1109\/tvt.2022.3189552","type":"journal-article","created":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T19:50:57Z","timestamp":1657569057000},"page":"12088-12103","source":"Crossref","is-referenced-by-count":66,"title":["Resource Allocation in UAV-Assisted Networks: A Clustering-Aided Reinforcement Learning Approach"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6824-8262","authenticated-orcid":false,"given":"Shiyang","family":"Zhou","sequence":"first","affiliation":[{"name":"National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-299X","authenticated-orcid":false,"given":"Yufan","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8137-0529","authenticated-orcid":false,"given":"Xia","family":"Lei","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2476-9028","authenticated-orcid":false,"given":"Qihang","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, UESTC, Sichuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4422-1705","authenticated-orcid":false,"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]},{"given":"Shaoqian","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China (UESTC), Chengdu, China"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Actor-critic reinforcement learning with energy-based policies","author":"heess","year":"0","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref38","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3003717"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3042462"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2892461"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3029225"},{"key":"ref37","first-page":"1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2920284"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2910263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023010"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2895831"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2854598"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6815890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3041347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3027695"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3047800"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2611512"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2900630"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3049367"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3043776"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/0105003"},{"key":"ref56","article-title":"CVX: MATLAB software for disciplined convex programming, version 2.2","author":"research","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref53","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/321694.321699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7470932"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref12","first-page":"1","article-title":"A survey of unmanned aerial vehicles (UAV) for traffic surveillance","author":"puri","year":"2005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/DSCC2008-2203"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2880467"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2877409"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2017.8288376"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2014.6881196"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2811942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2865922"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2790401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2922849"},{"key":"ref6","volume":"54","author":"austin","year":"2011","journal-title":"Unmanned Aircraft Systems UAVS Design Development and Deployment"},{"key":"ref5","first-page":"61","author":"stansbury","year":"2008","journal-title":"A Survey of UAS Technologies for Command Control and Communication (C3) in Unmanned Aircraft Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6852096"},{"key":"ref7","author":"valavanis","year":"2014","journal-title":"Handbook of Unmanned Aerial Vehicles"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2902559"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2954620"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012756"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3014788"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2342736"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2989319"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3018804"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC45663.2020.9120592"},{"key":"ref43","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9950228\/09826431.pdf?arnumber=9826431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:48:26Z","timestamp":1671479306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9826431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":56,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2022.3189552","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11]]}}}