{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:57:22Z","timestamp":1784822242179,"version":"3.55.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T00:00:00Z","timestamp":1686787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T00:00:00Z","timestamp":1686787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T00:00:00Z","timestamp":1686787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018919","name":"Major Key Project of the Peng Cheng Laboratory","doi-asserted-by":"publisher","award":["PCL2021A09-B2"],"award-info":[{"award-number":["PCL2021A09-B2"]}],"id":[{"id":"10.13039\/100018919","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6220012314"],"award-info":[{"award-number":["6220012314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2022-05078"],"award-info":[{"award-number":["RGPIN-2022-05078"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,6,15]]},"DOI":"10.1109\/jiot.2023.3237209","type":"journal-article","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T18:56:14Z","timestamp":1673981774000},"page":"10131-10145","source":"Crossref","is-referenced-by-count":82,"title":["Two-Timescale Learning-Based Task Offloading for Remote IoT in Integrated Satellite\u2013Terrestrial Networks"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1812-5501","authenticated-orcid":false,"given":"Dairu","family":"Han","sequence":"first","affiliation":[{"name":"Department of Aeronautical and Astronautical Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8208-6295","authenticated-orcid":false,"given":"Qiang","family":"Ye","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Memorial University of Newfoundland, St. John&#x2019;s, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7206-4706","authenticated-orcid":false,"given":"Haixia","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Xi&#x2019;an JiaoTong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0458-1282","authenticated-orcid":false,"given":"Wen","family":"Wu","sequence":"additional","affiliation":[{"name":"Frontier Research Center, Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3497-6437","authenticated-orcid":false,"given":"Huaqing","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhe","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Aeronautical and Astronautical Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2019.2909140"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OJVT.2021.3089083"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2875980"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2863124"},{"key":"ref36","article-title":"A closer look at invalid action masking in policy gradient algorithms","author":"huang","year":"2020","journal-title":"arXiv preprint arXiv 2006 14410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10226"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.2978856"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3135829"},{"key":"ref33","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc PMLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2012.6393515"},{"key":"ref32","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3029143"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3103320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3024186"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2978044"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3063697"},{"key":"ref38","year":"2021","journal-title":"ses-lic-intr2021&#x2013;02141"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3048818"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2988363"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3138898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3041347"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/8.633864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2990499"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2022.3169130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.2988787"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2021.9549118"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2826006"},{"key":"ref29","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume":"32","author":"li","year":"2019","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3075289"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3011963"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3133110"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000493"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3078433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3068596"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/sat.1245"},{"key":"ref40","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv preprint arXiv 1812 05905"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10142029\/10018447.pdf?arnumber=10018447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:15:09Z","timestamp":1687198509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10018447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,15]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3237209","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,15]]}}}