{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:46:21Z","timestamp":1776883581548,"version":"3.51.2"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T00:00:00Z","timestamp":1246406400000},"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. Automat. Contr."],"published-print":{"date-parts":[[2009,7]]},"DOI":"10.1109\/tac.2009.2022097","type":"journal-article","created":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T14:16:21Z","timestamp":1246457781000},"page":"1515-1531","source":"Crossref","is-referenced-by-count":52,"title":["Convergence Results for Some Temporal Difference Methods Based on Least Squares"],"prefix":"10.1109","volume":"54","author":[{"family":"Huizhen Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.P.","family":"Bertsekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2008.07.037"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref11","first-page":"49","article-title":"least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proc 16th Int Conf Machine Learning"},{"key":"ref12","author":"bertsekas","year":"1996","journal-title":"Temporal Differences-Based Policy Iteration and Applications in Neuro-Dynamic Programming"},{"key":"ref13","author":"konda","year":"2002","journal-title":"Actor-critic algorithms"},{"key":"ref14","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022192903948"},{"key":"ref17","author":"bertsekas","year":"2004","journal-title":"Learning and Approximate Dynamic Programming"},{"key":"ref18","first-page":"642","article-title":"a function approximation approach to estimation of policy gradient for pomdp with structured polices","author":"yu","year":"2005","journal-title":"Proc 11th Conf Uncertainty Artificial Intell"},{"key":"ref19","author":"sutton","year":"1998","journal-title":"Reinforcement Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.06.005"},{"key":"ref4","author":"gurvits","year":"1994","journal-title":"Incremental learning of evaluation functions for absorbing Markov chains New methods and theorems"},{"key":"ref27","first-page":"2368","article-title":"-learning algorithms for optimal stopping based on least squares","author":"yu","year":"2007","journal-title":"Proc Eur Control Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","author":"borkar","year":"2008","journal-title":"Stochastic Approximation A Dynamic Viewpoint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.7.1403"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017980312899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00099-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2008.4797685"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-12880-0","author":"duflo","year":"1997","journal-title":"Random Iterative Models"},{"key":"ref21","author":"ortega","year":"1970","journal-title":"Iterative Solution of Nonlinear Equations in Several Variables"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/A:1004641123405"},{"key":"ref23","author":"kushner","year":"2003","journal-title":"Stochastic Approximation and Recursive Algorithms and Applications"},{"key":"ref26","author":"yu","year":"2006","journal-title":"A Least Squares -Learning Algorithm for Optimal Stopping Problems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/9.793723"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9\/5159545\/05152964.pdf?arnumber=5152964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T23:51:54Z","timestamp":1633909914000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5152964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,7]]},"references-count":30,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tac.2009.2022097","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,7]]}}}