{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:20Z","timestamp":1784041100323,"version":"3.55.0"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1708700"],"award-info":[{"award-number":["2020YFB1708700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["U1909207"],"award-info":[{"award-number":["U1909207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC through the Autonomous Intelligent Unmanned Systems","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00107"],"award-info":[{"award-number":["226-2022-00107"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2023-00111"],"award-info":[{"award-number":["226-2023-00111"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Green Commun. Netw."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tgcn.2023.3295341","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T17:32:53Z","timestamp":1689269573000},"page":"2153-2162","source":"Crossref","is-referenced-by-count":13,"title":["Toward Scalable and Efficient Hierarchical Deep Reinforcement Learning for 5G RAN Slicing"],"prefix":"10.1109","volume":"7","author":[{"given":"Renlang","family":"Huang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7940-5590","authenticated-orcid":false,"given":"Miao","family":"Guo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2153-811X","authenticated-orcid":false,"given":"Chaojie","family":"Gu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1505-6766","authenticated-orcid":false,"given":"Shibo","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3155-3145","authenticated-orcid":false,"given":"Jiming","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5790-5025","authenticated-orcid":false,"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3131355"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3006199"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3088407"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3187138"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2019.106984"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3143949"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2705720"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.2991106"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3047843"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CAMAD50429.2020.9209299"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps52748.2021.9682073"},{"key":"ref13","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322106"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3136221"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041405"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092640"},{"key":"ref21","article-title":"Efficient object manipulation to an arbitrary goal pose: Learning-based anytime prioritized planning","author":"Xu","year":"2021","journal-title":"arXiv:2109.10583"},{"key":"ref22","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref23","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref24","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref25","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref26","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref28","first-page":"3050","article-title":"A deep reinforcement learning perspective on Internet congestion control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jay"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3016320"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11339"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/90.879343"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2009.5062017"},{"key":"ref34","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Kulkarni"}],"container-title":["IEEE Transactions on Green Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7511293\/10325381\/10183779.pdf?arnumber=10183779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T05:20:42Z","timestamp":1712899242000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10183779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":34,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tgcn.2023.3295341","relation":{},"ISSN":["2473-2400"],"issn-type":[{"value":"2473-2400","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}