{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T04:45:14Z","timestamp":1747889114283,"version":"3.41.0"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2015,11,1]],"date-time":"2015-11-01T00:00:00Z","timestamp":1446336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2015,11]]},"DOI":"10.1109\/tac.2015.2418411","type":"journal-article","created":{"date-parts":[[2015,4,1]],"date-time":"2015-04-01T22:32:10Z","timestamp":1427927530000},"page":"2989-2993","source":"Crossref","is-referenced-by-count":3,"title":["Classification-Based Approximate Policy Iteration"],"prefix":"10.1109","volume":"60","author":[{"given":"Amir-massoud","family":"Farahmand","sequence":"first","affiliation":[]},{"given":"Doina","family":"Precup","sequence":"additional","affiliation":[]},{"given":"Andre M. S.","family":"Barreto","sequence":"additional","affiliation":[]},{"given":"Mohammad","family":"Ghavamzadeh","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"424","article-title":"Reinforcement learning as classification: Leveraging modern classifiers","author":"lagoudakis","year":"0","journal-title":"Proc Int'l Conf Machine Learning (ICML '05)"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1613\/jair.1700","article-title":"Approximate policy iteration with a policy language bias: Solving relational Markov Decision Processes","volume":"25","author":"fern","year":"2006","journal-title":"J Artif Intell Res"},{"key":"ref12","first-page":"607","article-title":"Analysis of a classification-based policy iteration algorithm","author":"lazaric","year":"0","journal-title":"Proc Int'l Conf Machine Learning (ICML '05)"},{"key":"ref13","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Machine Learning Res"},{"key":"ref14","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Machine Learning Res"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1007\/b97848","author":"gy\u00f6rfi","year":"2002","journal-title":"A Distribution-Free Theory of Nonparametric Regression"},{"journal-title":"All of Nonparametric Statistics","year":"2007","author":"wasserman","key":"ref16"},{"key":"ref17","first-page":"1049","article-title":"Classification-based policy iteration with a critic","author":"gabillon","year":"0","journal-title":"Proc Int'l Conf Machine Learning (ICML '05)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/009053605000000282"},{"key":"ref19","first-page":"172","article-title":"Action-gap phenomenon in reinforcement learning","author":"farahmand","year":"0","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2009.5160611"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","author":"steinwart","year":"2008","journal-title":"Support Vector Machines"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553504"},{"key":"ref6","first-page":"1349","article-title":"Value pursuit iteration","author":"farahmand","year":"0","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref5","first-page":"1177","article-title":"Finite-sample analysis of Lasso-TD","author":"ghavamzadeh","year":"0","journal-title":"Proc Int'l Conf Machine Learning (ICML '05)"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1109\/TAC.2005.847037","article-title":"A basic formula for online policy gradient algorithms","volume":"50","author":"cao","year":"2005","journal-title":"IEEE Trans Autom Control"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/9.905687"},{"key":"ref2","first-page":"441","article-title":"Regularized policy iteration","author":"farahmand","year":"0","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref9","first-page":"457","article-title":"Bayesian policy gradient algorithms","author":"ghavamzadeh","year":"0","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01551-9","author":"szepesv\u00e1ri","year":"2010","journal-title":"Algorithms for Reinforcement Learning"},{"key":"ref20","article-title":"Generalized classification-based approximate policy iteration","author":"farahmand","year":"0","journal-title":"Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL)"},{"key":"ref22","article-title":"Classification-based approximate policy iteration: Experiments and extended discussions","author":"farahmand","year":"2014","journal-title":"arXiv e-print 1407 0449"},{"key":"ref21","article-title":"CAPI: Generalized classification-based approximate policy iteration","author":"farahmand","year":"0","journal-title":"Reinforcement Learning Decision Making (RLDM)"},{"key":"ref24","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc Artif Intell Stat (AISTATS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5254-7"},{"key":"ref26","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","author":"farahmand","year":"0","journal-title":"Proc Adv Neural Inform Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/040614384"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/7307243\/07076634.pdf?arnumber=7076634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T20:28:59Z","timestamp":1747859339000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7076634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11]]},"references-count":27,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2015.2418411","relation":{},"ISSN":["0018-9286","1558-2523"],"issn-type":[{"type":"print","value":"0018-9286"},{"type":"electronic","value":"1558-2523"}],"subject":[],"published":{"date-parts":[[2015,11]]}}}