{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T03:54:00Z","timestamp":1763178840423},"reference-count":21,"publisher":"Elsevier","isbn-type":[{"value":"9781558602472","type":"print"}],"license":[{"start":{"date-parts":[[1992,1,1]],"date-time":"1992-01-01T00:00:00Z","timestamp":694224000000},"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":[[1992]]},"DOI":"10.1016\/b978-1-55860-247-2.50063-2","type":"book-chapter","created":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T02:53:47Z","timestamp":1404183227000},"page":"451-457","source":"Crossref","is-referenced-by-count":16,"title":["Temporal Difference Learning of Backgammon Strategy"],"prefix":"10.1016","author":[{"given":"Gerald","family":"Tesauro","sequence":"first","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/B978-1-55860-247-2.50063-2_bib1","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1038\/scientificamerican0680-64","article-title":"\u201cComputer backgammon.\u201d","volume":"243","author":"Berliner","year":"1980","journal-title":"Sci. Am."},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib2","unstructured":"J. Christensen and R. Korf (1986). \u201cA unified theory of heuristic evaluation functions and its application to learning.\u201d Proc. of AAAI-86, 148\u2013152."},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib3","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/BF00992701","article-title":"\u201cTemporal differences: TD(\u03bb) for general \u03bb.\u201d","volume":"8","author":"Dayan","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib4","series-title":"Evolution, Games and Learning","article-title":"\u201cAlgorithmic strategies for improving the performance of game playing programs.\u201d","author":"Frey","year":"1986"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib5","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/0004-3702(74)90027-7","article-title":"\u201cA comparison and evaluation of three machine learning procedures as applied to the game of checkers.\u201d","volume":"5","author":"Griffith","year":"1974","journal-title":"Artificial Intelligence"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib6","article-title":"\u201cEscaping brittleness: the possibilities of general-purpose learning algorithms applied to parallel rule-based systems.\u201d","volume":"2","author":"Holland","year":"1986"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib7","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"\u201cMultilayer feedforward networks are universal approximators.\u201d","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0004-3702(88)90076-8","article-title":"\u201cA pattern classification approach to evaluation function learning.\u201d","volume":"36","author":"Lee","year":"1988","journal-title":"Artificial Intelligence"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib9","series-title":"Backgammon","author":"Magriel","year":"1976"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib10","series-title":"Perceptrons","author":"Minsky","year":"1969"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib11","unstructured":"D. H. Mitchell (1984). \u201cUsing features to evaluate positions in experts' and novices' Othello games.\u201d Master's Thesis, Northwestern Univ., Evanston, IL."},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib12","series-title":"Machine Learning","article-title":"\u201cLearning efficient classification procedures and their application to chess end games.\u201d","author":"Quinlan","year":"1983"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib13","article-title":"\u201cLearning internal representation by error propagation.\u201d","volume":"1","author":"Rumelhart","year":"1986"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib14","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1147\/rd.33.0210","article-title":"\u201cSome studies in machine learning using the game of checkers.\u201d","volume":"3","author":"Samuel","year":"1959","journal-title":"IBM J. of Research and Development"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib15","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1147\/rd.116.0601","article-title":"\u201cSome studies in machine learning using the game of checkers, II \u2013 recent progress.\u201d","volume":"11","author":"Samuel","year":"1967","journal-title":"IBM J. of Research and Development"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib16","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00115009","article-title":"\u201cLearning to predict by the methods of temporal differences.\u201d","volume":"3","author":"Sutton","year":"1988","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib17","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/0004-3702(89)90017-9","article-title":"\u201cA parallel network that learns to play backgammon.\u201d","volume":"39","author":"Tesauro","year":"1989","journal-title":"Artificial Intelligence"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib18","first-page":"99","article-title":"\u201cConnectionist learning of expert preferences by comparison training.\u201d","volume":"1","author":"Tesauro","year":"1989"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib19","doi-asserted-by":"crossref","unstructured":"G. Tesauro (1990). \u201cNeurogammon: a neural network backgammon program.\u201d IJCNN ProceedingsIII, 33\u201339.","DOI":"10.1109\/IJCNN.1990.137821"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib20","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1007\/BF00992697","article-title":"\u201cPractical issues in temporal difference learning.\u201d","volume":"8","author":"Tesauro","year":"1992","journal-title":"Machine Learning"},{"key":"10.1016\/B978-1-55860-247-2.50063-2_bib21","unstructured":"P. E. Utgoff and J. A. Clouse (1991). \u201cTwo kinds of training information for evaluation function training.\u201d Proc. of AAAI-91, 596\u2013600."}],"container-title":["Machine Learning Proceedings 1992"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558602472500632?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:B9781558602472500632?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T05:43:21Z","timestamp":1565588601000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558602472500632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1992]]},"ISBN":["9781558602472"],"references-count":21,"URL":"https:\/\/doi.org\/10.1016\/b978-1-55860-247-2.50063-2","relation":{},"subject":[],"published":{"date-parts":[[1992]]}}}