{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:25:31Z","timestamp":1791912331117,"version":"4.3.4"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2013,3,1]],"date-time":"2013-03-01T00:00:00Z","timestamp":1362096000000},"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. Signal Process."],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1109\/tsp.2012.2237171","type":"journal-article","created":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T19:02:29Z","timestamp":1357066949000},"page":"1460-1469","source":"Crossref","is-referenced-by-count":26,"title":["Online Learning Based Congestion Control for Adaptive Multimedia Transmission"],"prefix":"10.1109","volume":"61","author":[{"given":"Oussama","family":"Habachi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsien-Po","family":"Shiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mihaela","family":"van der Schaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yezekael","family":"Hayel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"318","article-title":"Learning internal representations by error backpropagation","author":"rumelhart","year":"1986","journal-title":"Parallel Distrib Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187178"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.1999.752152"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2177940"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070513"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.864313"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/90.793002"},{"key":"ref18","article-title":"A model based TCP-friendly rate control protocol","author":"padhye","year":"1999","journal-title":"Proc NOSSDAV"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/347057.347397"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2001.916251"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/9.24227"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843360"},{"key":"ref6","author":"littman","year":"1994","journal-title":"The Witness algorithm Solving partially observable Markov decision processes"},{"key":"ref5","first-page":"54","article-title":"Incremental pruning: A simple, fast, exact method for partially observable Markov decision process","author":"cassandra","year":"1997","journal-title":"Proc UAI"},{"key":"ref8","article-title":"First results with utile distinction memory for reinforcement learning","author":"mccallum","year":"1993","journal-title":"Conf Mach Des"},{"key":"ref7","first-page":"183","article-title":"Reinforcement learning with perceptual aliasing: The perceptual distinctions approach","author":"chrisman","year":"1992","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2003.12.002"},{"key":"ref9","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1352012.1352020"},{"key":"ref20","author":"putterman","year":"2005","journal-title":"Markov Decision Process Discrete Stochastic Dynamic Programming"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.26.2.282"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1071"},{"key":"ref24","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1613\/jair.761","article-title":"Speeding up the convergence of value iteration in partially observable Markov decision process","volume":"14","author":"zhang","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2000.832249"},{"key":"ref25","first-page":"1025","article-title":"Point-based value iteration: An anytime algorithm for POMDPS","author":"pineau","year":"2003","journal-title":"Proc Int Joint Conf Artif Intell (IJCAI)"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/78\/6463483\/06400258.pdf?arnumber=6400258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T20:55:56Z","timestamp":1638219356000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6400258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3]]},"references-count":28,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsp.2012.2237171","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,3]]}}}