{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:08:36Z","timestamp":1783966116224,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Sciences and Engineering Research Council of Canada DG","award":["#401864"],"award-info":[{"award-number":["#401864"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tnsm.2024.3481662","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T17:57:19Z","timestamp":1729101439000},"page":"807-821","source":"Crossref","is-referenced-by-count":6,"title":["Dynamic Policy Decision\/Enforcement Security Zoning Through Stochastic Games and Meta Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4518-0653","authenticated-orcid":false,"given":"Yahuza","family":"Bello","sequence":"first","affiliation":[{"name":"School of Engineering, University of Guelph, Guelph, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1540-9349","authenticated-orcid":false,"given":"Ahmed Refaey","family":"Hussein","sequence":"additional","affiliation":[{"name":"School of Engineering, University of Guelph, Guelph, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.062612.00056"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916180"},{"key":"ref5","volume-title":"Security Architecture and Procedures for 5G System","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3173031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2951818"},{"key":"ref8","article-title":"Zero trust architecture","author":"Stafford","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3200165"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3041042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3130418"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3063697"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3186834"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3276749"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2878570"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3293413"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3418897"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231618"},{"key":"ref21","first-page":"11909","article-title":"Generalized proximal policy optimization with sample reuse","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Queeney"},{"key":"ref22","first-page":"1","article-title":"Trust region-guided proximal policy optimization","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref24","article-title":"Sample dropout: A simple yet effective variance reduction technique in deep policy optimization","author":"Lin","year":"2023","journal-title":"arXiv:2302.02299"},{"key":"ref25","first-page":"113","article-title":"Truly proximal policy optimization","volume-title":"Proc. 35th Uncertain. Artif. Intell.","author":"Wang"},{"key":"ref26","article-title":"PTR-PPO: Proximal policy optimization with Prioritized trajectory replay","author":"Liang","year":"2021","journal-title":"arXiv:2112.03798"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF01769259"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3157248"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7748\/en.13.9.3.s8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/CNSM50824.2020.9269092"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5220\/0006197105590566"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/9781119723950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref35","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref36","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv:1707.03141"},{"key":"ref37","first-page":"1","article-title":"Optimization as a model for few-shot learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ravi"},{"key":"ref38","first-page":"1","article-title":"Meta-learning representations for continual learning","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Javed"},{"key":"ref39","first-page":"15254","article-title":"Meta-gradient reinforcement learning with an objective discovered online","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3148435"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3365902"},{"key":"ref42","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"Bai","year":"2022","journal-title":"arXiv:2202.11566"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.03.018"},{"key":"ref44","article-title":"You may not need ratio clipping in PPO","author":"Sun","year":"2022","journal-title":"arXiv:2202.00079"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4275028\/10927606\/10720151.pdf?arnumber=10720151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:40:46Z","timestamp":1742233246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2024.3481662","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}