{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:40:58Z","timestamp":1768344058472,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Research Fund (GRF) Project through the Hong Kong University Grants Committee","award":["14200720"],"award-info":[{"award-number":["14200720"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC) Project","doi-asserted-by":"publisher","award":["62073273"],"award-info":[{"award-number":["62073273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2022,5,1]]},"DOI":"10.1109\/jiot.2021.3111414","type":"journal-article","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T20:22:31Z","timestamp":1631218951000},"page":"6418-6433","source":"Crossref","is-referenced-by-count":22,"title":["Optimal Policy Characterization Enhanced Proximal Policy Optimization for Multitask Scheduling in Cloud Computing"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0077-8624","authenticated-orcid":false,"given":"Jiangliang","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-8032","authenticated-orcid":false,"given":"Yunjian","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2800693"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2017.2715817"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2815533"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2978830"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2986615"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2565516"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8648124"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2391491"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2710197"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2968913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2017.2711014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/321738.321743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.1998.726348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2601914"},{"key":"ref15","article-title":"Best-effort decision-making for real-time scheduling","author":"Locke","year":"1987"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2807924"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3046311"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2873658"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737559"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2864559"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2952647"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2611964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3033160"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2901850"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2990482"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2725277"},{"key":"ref29","first-page":"1","article-title":"Sample efficient actor-critic with experience replay","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref31","first-page":"1","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst. (NIPS)","author":"Wu"},{"key":"ref32","first-page":"6995","article-title":"Sample-optimal parametric Q-learning using linearly additive features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref33","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Schulman"},{"key":"ref34","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2740927"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2640453"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2541305"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2019.2901844"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2011.2182363"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875917"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2826006"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2678109"},{"key":"ref45","volume-title":"Stable Baselines","author":"Hill","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2011-169"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9762554\/09531963.pdf?arnumber=9531963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:06:46Z","timestamp":1705018006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9531963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,1]]},"references-count":46,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2021.3111414","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,1]]}}}