{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:34:44Z","timestamp":1768415684873,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg AI"},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tvt.2022.3202041","type":"journal-article","created":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T19:39:54Z","timestamp":1661542794000},"page":"546-556","source":"Crossref","is-referenced-by-count":8,"title":["Off-Policy Learning in Contextual Bandits for Remote Electrical Tilt Optimization"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7668-0650","authenticated-orcid":false,"given":"Filippo","family":"Vannella","sequence":"first","affiliation":[{"name":"Division of Decision and Control Systems at the School of EECS, KTH Royal Institute of Technology, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4533-3418","authenticated-orcid":false,"given":"Jaeseong","family":"Jeong","sequence":"additional","affiliation":[{"name":"Ericsson Research, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-4673","authenticated-orcid":false,"given":"Alexandre","family":"Proutiere","sequence":"additional","affiliation":[{"name":"Division of Decision and Control Systems at the School of EECS, KTH Royal Institute of Technology, Stockholm, Sweden"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Deep learning with logged bandit feedback","author":"joachims","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557040"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC50174.2021.9569387"},{"key":"ref30","article-title":"Self-optimization of coverage and capacity based on a fuzzy neural network with cooperative reinforcement learning","author":"shaoshuai","year":"2014","journal-title":"EURASIP J Wireless Commun Netw"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1935826.1935878"},{"key":"ref34","article-title":"Adam, a method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2013.6554660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2933420"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2010.5493665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2013.2276414"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VTCFall.2017.8288237"},{"key":"ref15","first-page":"1097","article-title":"Doubly robust policy evaluation and learning","author":"dud\u00edk","year":"0","journal-title":"Proc 28th Int Conf Int Conf Mach Learn"},{"key":"ref16","first-page":"814","article-title":"Counterfactual risk minimization: Learning from logged bandit feedback","author":"swaminathan","year":"0","journal-title":"Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref17","first-page":"3231","article-title":"The self-normalized estimator for counterfactual learning","author":"swaminathan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2013.2256441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2914040"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1002\/bltj.20463"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2011.5956370"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2419079"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6979983"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-016-3849-9"},{"key":"ref29","first-page":"19","article-title":"An unbiased offline evaluation of contextual bandit algorithms with generalized linear models","author":"li","year":"0","journal-title":"Proc Workshop On-line Trading Exploration Exploitation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2294965"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2016.2605380"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2012.6214334"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348456"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2011.0111"},{"key":"ref1","author":"waldhauser","year":"2011","journal-title":"Self-Organising Networks"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2798164"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCA54724.2022.9831850"},{"key":"ref26","article-title":"Coordinated reinforcement learning for optimizing mobile networks","author":"bouton","year":"0","journal-title":"Proc 35th Conf Neural Inf Process Syst Cooperative AI Workshops"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/6GNet54646.2022.9830258"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10017140\/09868108.pdf?arnumber=9868108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T23:04:37Z","timestamp":1676934277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9868108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":35,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2022.3202041","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}