{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T10:45:22Z","timestamp":1743763522775,"version":"3.37.3"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,2]]},"DOI":"10.1109\/infocom48880.2022.9796809","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:18:49Z","timestamp":1655759929000},"page":"2108-2117","source":"Crossref","is-referenced-by-count":7,"title":["Reinforcement Learning for Dynamic Dimensioning of Cloud Caches: A Restless Bandit Approach"],"prefix":"10.1109","author":[{"given":"Guojun","family":"Xiong","sequence":"first","affiliation":[{"name":"Suny-Binghamton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shufan","family":"Wang","sequence":"additional","affiliation":[{"name":"Suny-Binghamton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Yan","sequence":"additional","affiliation":[{"name":"Suny-Binghamton University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Suny-Binghamton University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901467"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v36i8.20852","article-title":"Reinforcement Learning Augmented Asymptotically Optimal Index Policies for Finite-Horizon Restless Bandits","author":"xiong","year":"2022","journal-title":"Proc Of AAAI"},{"key":"ref33","article-title":"Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits","author":"wang","year":"2020","journal-title":"Proc of NeurIPS"},{"key":"ref32","article-title":"Thompson Sampling in Non-Episodic Restless Bandits","author":"jung","year":"2019","journal-title":"arXiv preprint arXiv 1910 05656"},{"key":"ref31","article-title":"Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems","author":"jung","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34106-9_19"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ANZCC47194.2019.8945748"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2019.8919743"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/INDIANCC.2018.8307959"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2011.6120273"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2230215"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946895"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2198613"},{"year":"0","key":"ref2","article-title":"Amazon AWS"},{"key":"ref1","article-title":"Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2017-2022","author":"forecast","year":"2019","journal-title":"Update"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4064\/am2313-6-2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SCT.1994.315792"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1070.0505"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1287\/opre.48.1.80.12444","article-title":"Restless Bandits, Linear Programming Relaxations, and A Primal-Dual Index Heuristic","volume":"48","author":"bertsimas","year":"2000","journal-title":"Operations Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1239\/aap\/999187898"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/apr.2019.29"},{"key":"ref25","article-title":"An Asymptotically Optimal Index Policy for Finite-Horizon Restless Bandits","author":"hu","year":"2017","journal-title":"arXiv preprint arXiv 1707 00408"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"key":"ref51","article-title":"Learning Adversarial MDPs with Bandit Feedback and Unknown Transition","author":"jin","year":"2019","journal-title":"arXiv preprint arXiv 1912 01192"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1117\/12.774903"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680958"},{"key":"ref53","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i9.16979","article-title":"A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints","author":"kalagarla","year":"2021","journal-title":"Proc Of AAAI"},{"key":"ref52","article-title":"Online Convex Optimization in Adversarial Markov Decision Processes","author":"rosenberg","year":"2019","journal-title":"Proc of ICML"},{"key":"ref10","article-title":"Thompson Sampling for Learning Parameterized Markov Decision Processes","author":"gopalan","year":"2015","journal-title":"Proc of COLT"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2626384"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2844939"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2980105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/WIOPT.2018.8362806"},{"key":"ref16","article-title":"Dynacache: Dynamic Cloud Caching","author":"cidon","year":"2015","journal-title":"Proc of USENIX HotCloud"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068950"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946273"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2014.2374152"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"year":"0","key":"ref3","article-title":"Amazon Cloudfront"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/9780470980033"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2307\/3214163"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11750-007-0025-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/15-AAP1137"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2307\/3214547"},{"key":"ref9","article-title":"Near-Optimal Regret Bounds for Reinforcement Learning","volume":"11","author":"jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2562564"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1145\/2637364.2591983","article-title":"Index Policies for A Multi-Class Queue with Convex Holding Cost and Abandonments","author":"larra\u00f1aga","year":"2014","journal-title":"Proc of ACM SIGMETRICS"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437712"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107379"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737377"},{"key":"ref44","volume":"26","author":"baccelli","year":"2013","journal-title":"Elements of Queueing Theory Palm Martingale Calculus and Stochastic Recurrences"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92511-6_1"}],"event":{"name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","start":{"date-parts":[[2022,5,2]]},"location":"London, United Kingdom","end":{"date-parts":[[2022,5,5]]}},"container-title":["IEEE INFOCOM 2022 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9796607\/9796652\/09796809.pdf?arnumber=9796809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T08:03:05Z","timestamp":1727424185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9796809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/infocom48880.2022.9796809","relation":{},"subject":[],"published":{"date-parts":[[2022,5,2]]}}}