{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T01:47:59Z","timestamp":1714873679398},"reference-count":8,"publisher":"Elsevier","isbn-type":[{"value":"9781558603356","type":"print"}],"license":[{"start":{"date-parts":[[1994,1,1]],"date-time":"1994-01-01T00:00:00Z","timestamp":757382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1994]]},"DOI":"10.1016\/b978-1-55860-335-6.50040-4","type":"book-chapter","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T22:58:05Z","timestamp":1404169085000},"page":"266-274","source":"Crossref","is-referenced-by-count":2,"title":["On the Worst-case Analysis of Temporal-difference Learning Algorithms"],"prefix":"10.1016","author":[{"given":"Robert E.","family":"Schapire","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manfred K.","family":"Warmuth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib1","doi-asserted-by":"crossref","unstructured":"Nicol\u00f2 Cesa-Bianchi, Philip M. Long, and Manfred K. Warmuth. Worst-case quadratic loss bounds for a generalization of the Widrow-Hoff rule. In Proceedings of the Sixth Annual ACM Conference on Computational Learning Theory, pages 429\u2013438, July 1993.","DOI":"10.1145\/168304.168390"},{"issue":"3\/4","key":"10.1016\/B978-1-55860-335-6.50040-4_bib2","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1023\/A:1022632907294","article-title":"The convergence of TD(LD) for general LD","volume":"8","author":"Dayan","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib3","doi-asserted-by":"crossref","unstructured":"Peter Dayan and Terrence J. Sejnowski. TD(LD) converges with probability 1. Technical report, CNL, The Salk Institute, 1993.","DOI":"10.1007\/BF00993978"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib4","doi-asserted-by":"crossref","unstructured":"Tommi Jaakkola, Michael I. Jordan, and Satinder P. Singh. On the convergence of stochastic iterative dynamic programming algorithms. Technical Report 9307, MIT Computational Cognitive Science, July 1993:","DOI":"10.21236\/ADA276517"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib5","doi-asserted-by":"crossref","unstructured":"Jyrki Kivinen and Manfred K. Warmuth. Additive versus exponentiated gradient updates for learning linear functions. Technical Report UCSC-CRL-94\u201316, University of California Santa Cruz, Computer Research Laboratory, 1994.","DOI":"10.1145\/225058.225121"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib6","doi-asserted-by":"crossref","unstructured":"Nicholas Littlestone, Philip M. Long, and Manfred K. Warmuth. On-line learning of linear functions. In Proceedings of the Twenty Third Annual ACM Symposium on Theory of Computing, pages 465\u2013475, May 1991.","DOI":"10.1145\/103418.103467"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib7","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00115009","article-title":"Learning to predict by the methods of temporal differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-335-6.50040-4_bib8","unstructured":"C. J. C. H. Watkins. Learning from delayed rewards. PhD thesis, University of Cambridge, England, 1989."}],"container-title":["Machine Learning Proceedings 1994"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603356500404?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558603356500404?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T01:45:05Z","timestamp":1565574305000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558603356500404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994]]},"ISBN":["9781558603356"],"references-count":8,"URL":"https:\/\/doi.org\/10.1016\/b978-1-55860-335-6.50040-4","relation":{},"subject":[],"published":{"date-parts":[[1994]]}}}