{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:04:26Z","timestamp":1770739466637,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013114","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2023YFE0209100"],"award-info":[{"award-number":["2023YFE0209100"]}],"id":[{"id":"10.13039\/501100013114","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20310"],"award-info":[{"award-number":["U23A20310"]}],"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":["U21A20519"],"award-info":[{"award-number":["U21A20519"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"publisher","award":["MHP\/061\/23"],"award-info":[{"award-number":["MHP\/061\/23"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/jsac.2025.3608770","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T17:31:57Z","timestamp":1757611917000},"page":"866-882","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Task-Oriented Emergency-Aware UAV Crowdsensing: A Hierarchical Multi-Agent Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8386-2831","authenticated-orcid":false,"given":"Chen","family":"Fang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-329X","authenticated-orcid":false,"given":"Chi","family":"Harold Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0199-0488","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, SAR, China"}]},{"given":"Guangpeng","family":"Qi","sequence":"additional","affiliation":[{"name":"INSPUR Company Ltd., Jinan, China"}]},{"given":"Zhongyi","family":"Liu","sequence":"additional","affiliation":[{"name":"TravelSky Technology Ltd., Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1755-0183","authenticated-orcid":false,"given":"Dapeng","family":"Wu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, SAR, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3156632"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3157366"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3390693"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2874693"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3314826"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3110592"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3323522"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2011.5984917"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.65109\/LVZZ5205"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3331059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3345424"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3277482"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088693"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3307443"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3408603"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3123606"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229079"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2962457"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3147871"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155393"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29859"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3395493"},{"key":"ref25","article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","author":"de Witt","year":"2020","journal-title":"arXiv:2011.09533"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref27","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. ICLR","author":"Kuba"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1708"},{"key":"ref29","first-page":"34866","article-title":"HIQL: Offline goal-conditioned RL with latent states as actions","volume-title":"Proc. NeurIPS","author":"Park"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30132"},{"key":"ref31","article-title":"Hierarchical multi-agent DRL based dynamic cluster reconfiguration for UAV mobility management","author":"Meer","year":"2024","journal-title":"arXiv:2412.16167"},{"key":"ref32","article-title":"TAG: A decentralized framework for multi-agent hierarchical reinforcement learning","author":"Paolo","year":"2025","journal-title":"arXiv:2502.15425"},{"key":"ref33","first-page":"2783","article-title":"Goal-aware cross-entropy for multi-target reinforcement learning","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref34","first-page":"7750","article-title":"Maximum entropy gain exploration for long horizon multi-goal reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Pitis"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2902862"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088681"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2873606"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SARNOF.2006.4534773"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2864376"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2790401"},{"key":"ref41","first-page":"7057","article-title":"Dynamical distance learning for semi-supervised and unsupervised skill discovery","volume-title":"Proc. ICLR","author":"Hartikainen"},{"key":"ref42","first-page":"3025","article-title":"Prioritized experience replay","volume-title":"Proc. ICLR","author":"Schaul"},{"key":"ref43","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume-title":"Proc. NeurIPS","author":"Trott"},{"key":"ref44","volume-title":"CRAWDAD Dataset Epfl\/mobility (v. 2009-02-24)","author":"Piorkowski"},{"key":"ref45","volume-title":"Vehicular Trajectories Processing for Didi Gaia Open Data Set","author":"Xu","year":"2022"},{"key":"ref46","volume-title":"Support for Matrice 600\u2014DJI,","year":"2025"},{"key":"ref47","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3345280"},{"key":"ref49","first-page":"8622","article-title":"Adversarial intrinsic motivation for reinforcement learning","volume-title":"Proc. NeurIPS","author":"Durugkar"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2016.140952"},{"key":"ref51","volume-title":"NVIDIA,  Jetson Xavier Nx for Embedded & Edge Systems","year":"2025"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/49\/11372474\/11159270.pdf?arnumber=11159270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:06:40Z","timestamp":1770671200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11159270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/jsac.2025.3608770","relation":{},"ISSN":["1558-0008","0733-8716"],"issn-type":[{"value":"1558-0008","type":"electronic"},{"value":"0733-8716","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}