{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:28:35Z","timestamp":1780666115330,"version":"3.54.1"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":["CRII-CNS-NeTS-"],"award-info":[{"award-number":["CRII-CNS-NeTS-"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2104880"],"award-info":[{"award-number":["2104880"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["RINGS-2148309"],"award-info":[{"award-number":["RINGS-2148309"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Office of the"},{"name":"U","award":["0000DONOTUSETHIS0000.S"],"award-info":[{"award-number":["0000DONOTUSETHIS0000.S"]}]},{"name":"U","award":["DE-EE0009341"],"award-info":[{"award-number":["DE-EE0009341"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1109\/tnet.2023.3235480","type":"journal-article","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T18:39:08Z","timestamp":1674067148000},"page":"2147-2161","source":"Crossref","is-referenced-by-count":10,"title":["Reinforcement Learning for Dynamic Dimensioning of Cloud Caches: A Restless Bandit Approach"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5943-8109","authenticated-orcid":false,"given":"Guojun","family":"Xiong","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, 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":"Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7734-1589","authenticated-orcid":false,"given":"Gang","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, 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":"Department of Electrical and Computer Engineering, Binghamton University, State University of New York, Binghamton, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","year":"2021","journal-title":"Redis"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486316"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7552(96)00073-6"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155416"},{"key":"ref14","year":"2021","journal-title":"Amazon Web Service ElastiCache"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107379"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3492866.3549726"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20852"},{"key":"ref11","first-page":"861","article-title":"Thompson sampling for learning parameterized Markov decision processes","author":"gopalan","year":"2015","journal-title":"Proc 28th Conf Learn Theory"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901467"},{"key":"ref10","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"jaksch","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6848145"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2626384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2980105"},{"key":"ref18","first-page":"387","article-title":"19 Economic ecosystems in elastic wireless edge caching","author":"iosifidis","year":"2021","journal-title":"Wireless Edge Caching Modeling Analysis and Optimization"},{"key":"ref51","first-page":"1","article-title":"NeurWIN: Neural whittle index network for restless bandits via deep RL","author":"nakhleh","year":"2021","journal-title":"Proc NeurIPS"},{"key":"ref50","first-page":"1","article-title":"Learning index policies for restless bandits with application to maternal healthcare","author":"biswas","year":"2021","journal-title":"Proc AAMAS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919743"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/INDIANCC.2018.8307959"},{"key":"ref48","first-page":"1","article-title":"Restless-UCB, an efficient and low-complexity algorithm for online restless bandits","author":"wang","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ANZCC47194.2019.8945748"},{"key":"ref42","first-page":"1","article-title":"Regret bounds for Thompson sampling in episodic restless bandit problems","author":"jung","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_19"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2011.6120273"},{"key":"ref43","article-title":"Thompson sampling in non-episodic restless bandits","author":"hun jung","year":"2019","journal-title":"arXiv 1910 05654"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467370"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1214\/15-AAP1137"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/9780470980033"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11750-007-0025-0"},{"key":"ref4","year":"2021","journal-title":"Amazon CloudFront"},{"key":"ref3","year":"2021","journal-title":"Amazon AWS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/opre.48.1.80.12444"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/S0001867800010648"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/apr.2019.29"},{"key":"ref36","article-title":"An asymptotically optimal index policy for finite-horizon restless bandits","author":"hu","year":"2017","journal-title":"arXiv 1707 00205"},{"key":"ref31","first-page":"710","article-title":"Beyond ‘to act or not to act’: Fast Lagrangian approaches to general multi-action restless bandits","author":"killian","year":"2021","journal-title":"Proc AAMAS"},{"key":"ref30","first-page":"880","article-title":"Risk-aware interventions in public health: Planning with restless multi-armed bandits","author":"mate","year":"2021","journal-title":"Proc AAMAS"},{"key":"ref74","article-title":"On learning whittle index policy for restless bandits with scalable regret","author":"akbarzadeh","year":"2022","journal-title":"arXiv 2202 03463"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SCT.1994.315792"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1070.0505"},{"key":"ref2","author":"forecast","year":"2019","journal-title":"Cisco Visual Networking Index Global Mobile Data Traffic Forecast Update"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796809"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946895"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680958"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16979"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22099-4"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1117\/12.774903"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2014.2374152"},{"key":"ref68","article-title":"Learning adversarial MDPs with bandit feedback and unknown transition","author":"jin","year":"2019","journal-title":"arXiv 1912 01192"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946273"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-49819-5_6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2013.08.001"},{"key":"ref69","first-page":"5478","article-title":"Online convex optimization in adversarial Markov decision processes","author":"rosenberg","year":"2019","journal-title":"Proc ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2018.8362806"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437712"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2562564"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1017\/S0021900200039176"},{"key":"ref21","first-page":"1","article-title":"Dynacache: Dynamic cloud caching","author":"cidon","year":"2015","journal-title":"Proc USENIX HotCloud"},{"key":"ref65","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4064\/am2313-6-2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2025561"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2017.0697"},{"key":"ref60","volume":"26","author":"baccelli","year":"2013","journal-title":"Elements of Queueing Theory Palm Martingale Calculus and Stochastic Recurrences"},{"key":"ref62","first-page":"1","article-title":"Index policies for a multi-class queue with convex holding cost and abandonments","author":"larra naga","year":"2014","journal-title":"Proc ACM SIGMETRICS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2009.5062123"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/90\/10286433\/10021290-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10286433\/10021290.pdf?arnumber=10021290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T20:04:25Z","timestamp":1699301065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10021290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":74,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3235480","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]}}}