{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T22:01:30Z","timestamp":1746136890355,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927528","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T19:50:44Z","timestamp":1242762644000},"page":"74-81","source":"Crossref","is-referenced-by-count":21,"title":["Basis function adaptation methods for cost approximation in MDP"],"prefix":"10.1109","author":[{"given":"Huizhen","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Dimitri P.","family":"Bertsekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0161-1"},{"key":"15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-02431-3","author":"rockafellar","year":"1998","journal-title":"Variational Analysis"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.16.2.292"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"},{"key":"14","article-title":"a least squares q-learning algorithm for optimal stopping problems","volume":"2731","author":"yu","year":"2006","journal-title":"MIT Technical Report - LIDS"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2008.07.037"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/9.793723"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"3"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"10","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","author":"borkar","year":"2008","journal-title":"Stochastic Approximation A Dynamic Viewpoint"},{"key":"7","article-title":"least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proc The 16th Int Conf Machine Learning"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"5","volume":"2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control 3rd ed"},{"journal-title":"Reinforcement Learning","year":"1998","author":"sutton","key":"4"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.06.005"},{"key":"8","article-title":"improved temporal difference methods with linear function approximation","author":"bertsekas","year":"2004","journal-title":"Learning and Approximate Dynamic Programming"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2009,3,30]]},"location":"Nashville, TN, USA","end":{"date-parts":[[2009,4,2]]}},"container-title":["2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4910084\/4927513\/04927528.pdf?arnumber=4927528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T06:51:37Z","timestamp":1558335097000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4927528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927528","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}