{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:02:54Z","timestamp":1730196174864,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,9]]},"DOI":"10.1109\/allerton.2008.4797685","type":"proceedings-article","created":{"date-parts":[[2009,3,9]],"date-time":"2009-03-09T15:05:03Z","timestamp":1236611103000},"page":"1116-1123","source":"Crossref","is-referenced-by-count":3,"title":["New error bounds for approximations from projected linear equations"],"prefix":"10.1109","author":[{"given":"Huizhen","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dimitri P.","family":"Bertsekas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"15","article-title":"error bounds for approximate policy iteration","author":"munos","year":"2003","journal-title":"Proc The 20th Int Conf Machine Learning"},{"journal-title":"A least squares Q-learning algorithm for optimal stopping problems","year":"2006","author":"yu","key":"13"},{"journal-title":"On regression based stopping times","year":"2007","author":"van roy","key":"14"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/9.793723"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"3"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"10","article-title":"least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proc The 16th Int Conf Machine Learning"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00099-0"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2008.07.037"},{"key":"5","volume":"2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"journal-title":"Reinforcement Learning","year":"1998","author":"sutton","key":"4"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2008.4797685"}],"event":{"name":"2008 46th Annual Allerton Conference on Communication, Control, and Computing","start":{"date-parts":[[2008,9,23]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2008,9,26]]}},"container-title":["2008 46th Annual Allerton Conference on Communication, Control, and Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4786970\/4797526\/04797685.pdf?arnumber=4797685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T22:59:02Z","timestamp":1489791542000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4797685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,9]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/allerton.2008.4797685","relation":{},"subject":[],"published":{"date-parts":[[2008,9]]}}}