{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:23:34Z","timestamp":1729671814420,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927518","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T15:50:44Z","timestamp":1242748244000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["A unified framework for temporal difference methods"],"prefix":"10.1109","author":[{"given":"Dimitri P.","family":"Bertsekas","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"a least squares q-learning algorithm for optimal stopping problems","author":"yu","year":"2007","journal-title":"Lab for Info and Dec Sys Report 2731 MIT"},{"doi-asserted-by":"publisher","key":"17","DOI":"10.1109\/9.580874"},{"doi-asserted-by":"publisher","key":"18","DOI":"10.1109\/TAC.2009.2022097"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning","key":"15"},{"doi-asserted-by":"publisher","key":"16","DOI":"10.1007\/BF00115009"},{"year":"2003","author":"pang","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems","key":"13"},{"key":"14","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"year":"2002","author":"konda","journal-title":"Actor-critic algorithms","key":"11"},{"key":"12","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","article-title":"least squares policy evaluation algorithms with linear function approximation","volume":"13","author":"nedic?","year":"2003","journal-title":"Discrete Event Dynamic Systems Theory and Applications"},{"key":"3","article-title":"temporal differences-based policy iteration and applications in neuro-dynamic programming","author":"bertsekas","year":"1996","journal-title":"Lab for Info and Decision Systems Report LIDS-P-2349 MIT"},{"key":"2","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1007\/BFb0120965","article-title":"projection methods for variational inequalities with applications to the traffic assignment problem","volume":"17","author":"bertsekas","year":"1982","journal-title":"Mathemat Prog Study"},{"key":"1","article-title":"improved temporal difference methods with linear function approximation","author":"bertsekas","year":"2004","journal-title":"Learning and Approximate Dynamic Programming"},{"doi-asserted-by":"publisher","key":"10","DOI":"10.1007\/s10626-006-8134-8"},{"doi-asserted-by":"publisher","key":"7","DOI":"10.1016\/j.cam.2008.07.037"},{"year":"1996","author":"bertsekas","journal-title":"Neuro-Dynamic Programming","key":"6"},{"year":"1989","author":"bertsekas","journal-title":"Parallel and Distributed Computation Numerical Methods Prentice-Hall Englewood Cliffs N J","key":"5"},{"key":"4","volume":"2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"doi-asserted-by":"publisher","key":"9","DOI":"10.1007\/BF00114723"},{"doi-asserted-by":"publisher","key":"8","DOI":"10.1023\/A:1017936530646"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","start":{"date-parts":[[2009,3,30]]},"location":"Nashville, TN","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\/04927518.pdf?arnumber=4927518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T19:05:00Z","timestamp":1633460700000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/4927518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927518","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}