{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:19:39Z","timestamp":1780586379770,"version":"3.54.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2148309"],"award-info":[{"award-number":["2148309"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2315614"],"award-info":[{"award-number":["2315614"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"crossref","award":["W911NF-23-1-0072"],"award-info":[{"award-number":["W911NF-23-1-0072"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"crossref","award":["DE-EE0009341"],"award-info":[{"award-number":["DE-EE0009341"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"publisher","award":["SRG\/2021\/002308"],"award-info":[{"award-number":["SRG\/2021\/002308"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnet.2024.3417351","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T17:33:53Z","timestamp":1719250433000},"page":"4286-4301","source":"Crossref","is-referenced-by-count":7,"title":["Whittle Index-Based Q-Learning for Wireless Edge Caching With Linear Function Approximation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5943-8109","authenticated-orcid":false,"given":"Guojun","family":"Xiong","sequence":"first","affiliation":[{"name":"Departments of Applied Mathematics and Statistics, and Computer Science, Data Science Program, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0284-5683","authenticated-orcid":false,"given":"Shufan","family":"Wang","sequence":"additional","affiliation":[{"name":"Departments of Applied Mathematics and Statistics, and Computer Science, Data Science Program, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3642-3569","authenticated-orcid":false,"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Departments of Applied Mathematics and Statistics, and Computer Science, Data Science Program, Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0363-3666","authenticated-orcid":false,"given":"Rahul","family":"Singh","sequence":"additional","affiliation":[{"name":"Indian Institute of Science, Bengaluru, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2012.120401"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/3214547"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/15-AAP1137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11750-007-0025-0"},{"issue":"4","key":"ref7","first-page":"1","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","first-page":"861","article-title":"Thompson sampling for learning parameterized Markov decision processes","volume-title":"Proc. COLT","author":"Gopalan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110186"},{"key":"ref10","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","volume":"48","author":"Borkar","year":"2009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844939"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2850818"},{"key":"ref13","first-page":"1","article-title":"Achieving freshness in single\/multi-user caching of dynamic content over the wireless edge","volume-title":"Proc. 18th Int. Symp. Model. Optim. Mobile, Ad Hoc, Wireless Netw. (WiOPT)","author":"Abolhassani"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2913677"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3152042.3152050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901467"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486316"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2956041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844919"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2936193"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844985"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155373"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413524"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494855"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2562564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2591983"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SCT.1994.315792"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_19"},{"key":"ref31","first-page":"1","article-title":"Regret bounds for Thompson sampling in episodic restless bandit problems","volume-title":"Proc. NIPS","author":"Jung"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ANZCC47194.2019.8945748"},{"key":"ref33","first-page":"11878","article-title":"Restless-UCB, an efficient and low-complexity algorithm for online restless bandits","volume-title":"Proc. NIPS","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3512798.3512816"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3670686"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3492866.3549726"},{"key":"ref38","first-page":"1","article-title":"DeepTOP: Deep threshold-optimal policy for MDPs and RMABs","volume-title":"Proc. NIPS","author":"Nakhleh"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3235480"},{"key":"ref40","first-page":"17911","article-title":"Learning infinite-horizon average-reward restless multi-action bandits via index awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xiong"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102000"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-11657-9"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422142"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1287\/opre.9.3.383"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3171626"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2936199"},{"issue":"2","key":"ref47","volume-title":"Dynamic Programming and Optimal Control","volume":"1","author":"Bertsekas","year":"1995"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012999361974"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704593"},{"key":"ref50","first-page":"1","article-title":"Model-free reinforcement learning in infinite-horizon average-reward Markov decision processes","volume-title":"Proc. ICML","author":"Wei"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/556"},{"key":"ref52","article-title":"Nonlinear two-time-scale stochastic approximation: Convergence and finite-time performance","author":"Doan","year":"2020","journal-title":"arXiv:2011.01868"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919880"},{"key":"ref54","article-title":"Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning","author":"Chen","year":"2019","journal-title":"arXiv:1905.11425"},{"key":"ref55","first-page":"1","article-title":"Finite-time performance bounds and adaptive learning rate selection for two time-scale reinforcement learning","volume-title":"Proc. NIPS","author":"Gupta"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3392143"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2931688"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2968326"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680958"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1117\/12.774903"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.19.7.717"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/90\/10720541\/10570315-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/90\/10720541\/10570315.pdf?arnumber=10570315","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:37:15Z","timestamp":1729226235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570315\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":61,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3417351","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}