{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T22:23:01Z","timestamp":1774736581719,"version":"3.50.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1109\/tit.2017.2773526","type":"journal-article","created":{"date-parts":[[2017,11,14]],"date-time":"2017-11-14T19:11:45Z","timestamp":1510686705000},"page":"4610-4628","source":"Crossref","is-referenced-by-count":15,"title":["Online Learning Schemes for Power Allocation in Energy Harvesting Communications"],"prefix":"10.1109","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2459-6289","authenticated-orcid":false,"given":"Pranav","family":"Sakulkar","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9994-9931","authenticated-orcid":false,"given":"Bhaskar","family":"Krishnamachari","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2258656"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.07.080544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref15","first-page":"817","article-title":"The epoch-greedy algorithm for multi-armed bandits with side information","author":"langford","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"169","article-title":"Efficient optimal learning for contextual bandits","author":"dudik","year":"2011","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref17","first-page":"1638","article-title":"Taming the monster: A fast and simple algorithm for contextual bandits","author":"agarwal","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","article-title":"Stochastic contextual bandits with known reward functions","author":"sakulkar","year":"2016"},{"key":"ref19","first-page":"49","article-title":"Logarithmic online regret bounds for undiscounted reinforcement learning","volume":"19","author":"ortner","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110921"},{"key":"ref27","article-title":"Efficient scheduling for energy-delay tradeoff on a time-slotted channel","author":"wu","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.012412.110805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2012.6176889"},{"key":"ref29","author":"levin","year":"2009","journal-title":"Markov Chains and Mixing Times"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2009.070905"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2199984"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2012.022912.110298"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2011.112811.100349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2263494"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2015.2391531"},{"key":"ref20","first-page":"89","article-title":"Near-optimal regret bounds for reinforcement learning","author":"auer","year":"0","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref22","author":"ross","year":"1983","journal-title":"Introduction to Stochastic Dynamic Programming"},{"key":"ref21","first-page":"1505","article-title":"Optimistic linear programming gives logarithmic regret for irreducible mdps","author":"tewari","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","first-page":"1","article-title":"CVXPY: A python-embedded modeling language for convex optimization","volume":"17","author":"diamond","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref23","author":"puterman","year":"2005","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/moor.22.1.222"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM.2016.7746654"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/8361085\/08107579.pdf?arnumber=8107579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T07:27:37Z","timestamp":1643182057000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8107579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":29,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tit.2017.2773526","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}