{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:04:05Z","timestamp":1759385045427,"version":"3.44.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62372323"],"award-info":[{"award-number":["62372323"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Key Foundation of China","doi-asserted-by":"publisher","award":["62032016"],"award-info":[{"award-number":["62032016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tce.2025.3544802","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T13:31:04Z","timestamp":1741008664000},"page":"3790-3801","source":"Crossref","is-referenced-by-count":1,"title":["Self-Organization Scheduling of Dynamic AAV-MD Networks via Three-Layer Hierarchical Reinforcement Learning"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5140-3406","authenticated-orcid":false,"given":"Qiao","family":"Liao","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8158-7453","authenticated-orcid":false,"given":"Zhiyong","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3572-8478","authenticated-orcid":false,"given":"Hongyue","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4430-4765","authenticated-orcid":false,"given":"Shizhan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3361394"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2300020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3368156"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3372785"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2023.3349079"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3371163"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986615"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3071531"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2923702"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2789293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2954944"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9163048"},{"key":"ref14","article-title":"Mobile edge computation offloading using game theory and rein-forcement learning","author":"Ranadheera","year":"2017","journal-title":"arXiv:1711.09012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2725277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2810292"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2949997"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2955035"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2890133"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1151690.1151693"},{"key":"ref21","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2927313"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-79392-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2958975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2760281"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC.2019.8766458"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2022.3150432"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2020.3036871"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2019.2928811"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2022.3148254"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2021.3059691"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21236\/ADA276517"},{"volume-title":"Parallel and Distributed Computation","year":"1989","author":"Bertsekas","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2024.3394859"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3414140"},{"volume-title":"RLlib: Industry-grade, scalable reinforcement learning","year":"2025","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3416432"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/lwc.2024.3377444"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3381834"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.004.2100694"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2020.100282"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11128999\/10909242.pdf?arnumber=10909242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:16:35Z","timestamp":1755627395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10909242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":43,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3544802","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"type":"print","value":"0098-3063"},{"type":"electronic","value":"1558-4127"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}