{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T04:52:42Z","timestamp":1776487962973,"version":"3.51.2"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018YFB1801105"],"award-info":[{"award-number":["2018YFB1801105"]}]},{"name":"Programme of Introducing Talents of Discipline to Universities","award":["B20064"],"award-info":[{"award-number":["B20064"]}]},{"name":"National Science and Technology Council","award":["111-2221-E-A49-197-MY3"],"award-info":[{"award-number":["111-2221-E-A49-197-MY3"]}]},{"name":"National Science and Technology Council","award":["112-2218-E-194-005-"],"award-info":[{"award-number":["112-2218-E-194-005-"]}]},{"name":"National Science and Technology Council","award":["112-2218-E-305-001-"],"award-info":[{"award-number":["112-2218-E-305-001-"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/twc.2023.3323554","type":"journal-article","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T02:47:21Z","timestamp":1707878841000},"page":"4932-4949","source":"Crossref","is-referenced-by-count":16,"title":["Collaborative Computing in Non-Terrestrial Networks: A Multi-Time-Scale Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-4066","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4347-2871","authenticated-orcid":false,"given":"Shao-Yu","family":"Lien","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Systems, National Yang Ming Chiao Tung University, Tainan City, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2671-5090","authenticated-orcid":false,"given":"Ying-Chang","family":"Liang","sequence":"additional","affiliation":[{"name":"Center for Intelligent Networking and Communications (CINC), University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}]},{"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, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/pimrc56721.2023.10294047"},{"key":"ref2","volume-title":"Solutions for NR to Support Non-Terrestrial Networks","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.011.2100038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3134246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3052542"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2885747"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref8","article-title":"A dynamic codebook design for analog beamforming in MIMO LEO satellite communications","author":"Palacios","year":"2021","journal-title":"arXiv:2111.08655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771777"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3131573"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625309"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3019437"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3145848"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP52444.2021.9651962"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3141120"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.011.2100162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2893898"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2898002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3237209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3214110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.1600058WC"},{"key":"ref23","article-title":"Multi-pass Q-networks for deep reinforcement learning with parameterised action spaces","author":"Bester","year":"2019","journal-title":"arXiv:1905.04388"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.812782"},{"key":"ref25","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref27","first-page":"1","article-title":"Sub-policy adaptation for hierarchical reinforcement learning","volume-title":"Proc. ICML","author":"Li"},{"key":"ref28","article-title":"A game-theoretic approach to multi-agent trust region optimization","author":"Wen","year":"2021","journal-title":"arXiv:2106.06828"},{"key":"ref29","first-page":"1","article-title":"Stackelberg MADDPG: Learning emergent behaviors via information asymmetry in competitive games","volume-title":"Proc. AAAI","author":"Yang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003814"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Schulman"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"key":"ref33","volume-title":"Study on Channel Model for Frequencies From 0.5 to 100 GHz","year":"2019"},{"key":"ref34","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2919611"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10527220\/10299604.pdf?arnumber=10299604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T05:35:40Z","timestamp":1715319340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10299604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":36,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/twc.2023.3323554","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}