{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:00:09Z","timestamp":1775066409756,"version":"3.50.1"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20444"],"award-info":[{"award-number":["U21A20444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971366"],"award-info":[{"award-number":["61971366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2049"],"award-info":[{"award-number":["U20B2049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61822207"],"award-info":[{"award-number":["61822207"]}],"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":["2042021gf0006"],"award-info":[{"award-number":["2042021gf0006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tifs.2022.3149396","type":"journal-article","created":{"date-parts":[[2022,2,7]],"date-time":"2022-02-07T20:50:57Z","timestamp":1644267057000},"page":"732-743","source":"Crossref","is-referenced-by-count":62,"title":["Safe Exploration in Wireless Security: A Safe Reinforcement Learning Algorithm With Hierarchical Structure"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8247-0353","authenticated-orcid":false,"given":"Xiaozhen","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2402-611X","authenticated-orcid":false,"given":"Liang","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Guohang","family":"Niu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8967-8525","authenticated-orcid":false,"given":"Qian","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2856854"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2019.2904486"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3056206"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024860"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2878718"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3010967"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2785414"},{"key":"ref9","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Tessler"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682983"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3007742"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref13","first-page":"3675","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Kulkarni"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09430-0"},{"key":"ref15","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"3","key":"ref16","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"issue":"1","key":"ref19","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"Barto","year":"2003","journal-title":"Discrete Event Dyn. Syst."},{"key":"ref20","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"Vezhnevets","year":"2017","journal-title":"arXiv:1703.01161"},{"key":"ref21","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Nachum"},{"issue":"1","key":"ref22","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","first-page":"14093","article-title":"Reinforcement learning with convex constraints","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Miryoosefi"},{"key":"ref24","first-page":"3127","article-title":"Convergent policy optimization for safe reinforcement learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Yu"},{"key":"ref25","first-page":"1","article-title":"Actor-Mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Parisotto"},{"key":"ref26","first-page":"4868","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Jin"},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2945167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485863"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.2972328"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2015.2492556"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/9652463\/09705557.pdf?arnumber=9705557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T22:51:46Z","timestamp":1705531906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9705557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/tifs.2022.3149396","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}