{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T07:23:39Z","timestamp":1742801019724},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T00:00:00Z","timestamp":1380585600000},"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 J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1109\/jstsp.2013.2255022","type":"journal-article","created":{"date-parts":[[2013,3,27]],"date-time":"2013-03-27T18:04:05Z","timestamp":1364407445000},"page":"746-758","source":"Crossref","is-referenced-by-count":5,"title":["Feature Search in the Grassmanian in Online Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"given":"Shalabh","family":"Bhatnagar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek S.","family":"Borkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prabuchandran","family":"K. J.","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref31","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927528"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00099-0"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2008.07.037"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/858481.858486"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-4285-0","author":"bhatnagar","year":"2013","journal-title":"Stochastic Recursive Algorithms for Optimization Simultaneous Perturbation Methods"},{"key":"ref13","author":"bhatnagar","year":"2012","journal-title":"Chapter 23 of Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref14","article-title":"Adaptive Feature Tuning in the Grassmanian in Online Reinforcement Learning","author":"bhatnagar","year":"0","journal-title":"Dept of Comput Sci Indian Inst of Science IISc-CSA-SSL-TR-2013-2 March-2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012995282784"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","author":"borkar","year":"2008","journal-title":"Stochastic Approximation A Dynamical Systems Viewpoint"},{"key":"ref18","first-page":"49","author":"boyan","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref19","first-page":"312","article-title":"Adaptive bases for reinforcement learning","volume":"6321","author":"di castro","year":"2010","journal-title":"Mach Learn Knowl Discovery in Databases Proc Eur Conf Mach Learn Barcelona Spain"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2000.912220"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273589"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5706976"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75894-2"},{"key":"ref29","article-title":"Incremental basis construction from temporal difference error","author":"sun","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2008.03.003"},{"key":"ref8","author":"bertsekas","year":"2011","journal-title":"Dynamic Programming and Optimal Control Vol II (4th ed )"},{"key":"ref7","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control Vol I (3rd ed )"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref9","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400830244"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895290954"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-9352-8","author":"kushner","year":"1978","journal-title":"Stochastic Approximation Methods for Constrained and Unconstrained Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143901"},{"key":"ref24","article-title":"Convergent temporal-difference learning with arbitrary smooth function approximation","author":"maei","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-2696-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"ref25","article-title":"Basis construction from power series expansions of value functions","author":"mahadevan","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/6595546\/06488714.pdf?arnumber=6488714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,12]],"date-time":"2022-02-12T14:27:31Z","timestamp":1644676051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6488714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":35,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2013.2255022","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10]]}}}