{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T10:26:16Z","timestamp":1777717576487,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002920","name":"General Research Fund","doi-asserted-by":"publisher","award":["14200420"],"award-info":[{"award-number":["14200420"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tnnls.2021.3085088","type":"journal-article","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T19:44:52Z","timestamp":1623354292000},"page":"7448-7460","source":"Crossref","is-referenced-by-count":5,"title":["A Reinforcement Learning Approach to Price Cloud Resources With Provable Convergence Guarantees"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7935-7210","authenticated-orcid":false,"given":"Hong","family":"Xie","sequence":"first","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C. S.","family":"Lui","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2013.48"},{"key":"ref38","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1120.1066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2016.2657"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2957092"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2200\/S00505ED1V01Y201305CNT013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1111\/1756-2171.12304"},{"key":"ref34","article-title":"Strategic dynamic pricing with network effects","author":"makhdoumi","year":"2017","journal-title":"Proc Rotman School Manage Working Paper"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2745844.2745855"},{"key":"ref40","author":"wolski","year":"2014","journal-title":"Dataset"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2016.2609844"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524440"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078529"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017570"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud.2018.00076"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2013.15"},{"key":"ref17","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"ref19","first-page":"67","article-title":"Using reinforcement learning for autonomic resource allocation in clouds: Towards a fully automated workflow","author":"dutreilh","year":"2011","journal-title":"Proc ICAS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00011-O"},{"key":"ref4","author":"hardy","year":"2017","journal-title":"Google Races to Catch Up in Cloud Computing"},{"key":"ref27","first-page":"2235","article-title":"Zap Q-learning","author":"devraj","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","author":"hardy","year":"2017","journal-title":"Why the Computing Cloud Will Keep Growing and Growing"},{"key":"ref6","author":"williams","year":"2012","journal-title":"The economics of cloud Computing an overview for decision makers"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/restud\/rdq007"},{"key":"ref5","year":"2014","journal-title":"Amazon EC2 Spot Instances Pricing Amazon EC2 Spot Instances Pricing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2013.6550265"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2010.92"},{"key":"ref2","author":"wingfield","year":"2017","journal-title":"Amazon’s Cloud Business Lifts its Profit to a Record"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2591971.2591980"},{"key":"ref1","author":"team","year":"2017","journal-title":"Microsoft’s Cloud Services Boost Revenues"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2011.10.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.7553036"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.2864"},{"key":"ref24","first-page":"139","article-title":"Optimal pricing for the competitive and evolutionary cloud market","author":"xu","year":"2015","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2017.15"},{"key":"ref26","first-page":"2411","article-title":"Speedy Q-learning","author":"azar","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"Learning from delayed rewards","author":"watkins","year":"1989"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9966944\/09451547.pdf?arnumber=9451547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:55:36Z","timestamp":1671479736000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9451547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3085088","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}