{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:43:33Z","timestamp":1785336213202,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018YFB1800502"],"award-info":[{"award-number":["2018YFB1800502"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671079"],"award-info":[{"award-number":["61671079"]}],"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":["61771068"],"award-info":[{"award-number":["61771068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["4182041"],"award-info":[{"award-number":["4182041"]}]},{"name":"Ministry of Education and China Mobile Joint Fund","award":["MCM20180101"],"award-info":[{"award-number":["MCM20180101"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2019130"],"award-info":[{"award-number":["CX2019130"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cloud Comput."],"published-print":{"date-parts":[[2022,4,1]]},"DOI":"10.1109\/tcc.2020.2985651","type":"journal-article","created":{"date-parts":[[2020,4,6]],"date-time":"2020-04-06T19:37:01Z","timestamp":1586201821000},"page":"1262-1274","source":"Crossref","is-referenced-by-count":14,"title":["Towards Intelligent Provisioning of Virtualized Network Functions in Cloud of Things: A Deep Reinforcement Learning Based Approach"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1301-4981","authenticated-orcid":false,"given":"Bo","family":"He","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2182-2228","authenticated-orcid":false,"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0829-4624","authenticated-orcid":false,"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-7422","authenticated-orcid":false,"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1486-0573","authenticated-orcid":false,"given":"Jianxin","family":"Liao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2015.7368826"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759218"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2705560"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2767608"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2759728"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2746186"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2015.2485206"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2889482"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2013.6581037"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2016.2526007"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2800003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098826"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2016.2525342"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2017.7996870"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2880754"},{"key":"ref16","volume-title":"Introduction to Reinforcement Learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11339"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MCC.2018.1081063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2844243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref22","first-page":"3555","article-title":"Multi-layered gradient boosting decision trees","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Feng"},{"key":"ref23","first-page":"5285","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref24","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. 14th Int. Conf. Neural Inf. Process. Syst.","author":"Kakade"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1163593.1163596"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1129582.1129589"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2017.03.019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2019.2944823"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2747560"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2018.01.007"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2016.2543722"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2019.2947900"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25258-2_8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254756"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2864101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3138808.3138810"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2018.11.009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2017.2782370"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2017.2686979"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.06.003"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00097"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3326285.3329056"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref45","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2018.8297294"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2814606"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/497"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref50","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref51","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref52","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref53","article-title":"Policy optimization with penalized point probability distance: An alternative to proximal policy optimization","author":"Chu","year":"2018"},{"key":"ref54","first-page":"2408","article-title":"Optimizing neural networks with kronecker-factored approximate curvature","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Martens"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5220\/0006105602530262"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"ref57","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2683200"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2786639"}],"container-title":["IEEE Transactions on Cloud Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6245519\/9789509\/09057687.pdf?arnumber=9057687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:33:19Z","timestamp":1704839599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9057687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":60,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcc.2020.2985651","relation":{},"ISSN":["2168-7161","2372-0018"],"issn-type":[{"value":"2168-7161","type":"electronic"},{"value":"2372-0018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,1]]}}}