{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:00:38Z","timestamp":1729638038803,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,9]]},"DOI":"10.1109\/cig.2012.6374141","type":"proceedings-article","created":{"date-parts":[[2012,12,12]],"date-time":"2012-12-12T22:02:44Z","timestamp":1355349764000},"page":"79-82","source":"Crossref","is-referenced-by-count":6,"title":["Imitating play from game trajectories: Temporal difference learning versus preference learning"],"prefix":"10.1109","author":[{"given":"Thomas Philip","family":"Runarsson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon M.","family":"Lucas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"10","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/978-3-642-25566-3_20","article-title":"Supervised learning linear priority dispatch rules for job-shop scheduling","volume":"6683","author":"ingimundardottir","year":"2011","journal-title":"Lecture Notes in Computer Science"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_30"},{"key":"6","first-page":"1246","article-title":"Focus of attention in reinforcement learning","volume":"13","author":"li","year":"2007","journal-title":"Journal of Universal Computer Science"},{"key":"5","first-page":"424","article-title":"Reinforcement learning as classification: Leveraging modern classifiers","volume":"20","author":"lagoudakis","year":"2003","journal-title":"ICML"},{"key":"4","article-title":"Analysis of a classification-based policy iteration algorithm","author":"lazaric","year":"0","journal-title":"Proceedings of the 27 Th International Conference on Machine Learning 2010"},{"key":"9","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1613\/jair.179","article-title":"Statistical feature combination for the evaluation of game positions","volume":"3","author":"buro","year":"1995","journal-title":"JAIR"},{"key":"8","article-title":"Experiments with Multi-ProbCut and a new high-quality evaluation function for Othello","author":"buro","year":"1997","journal-title":"Games in AI Research"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2005.09.047"},{"key":"12","first-page":"1","article-title":"Learning to Play Othello with N-Tuple Systems","volume":"4","author":"lucas","year":"2008","journal-title":"Australian Journal of Intelligent Information Processing"}],"event":{"name":"2012 IEEE Conference on Computational Intelligence and Games (CIG)","start":{"date-parts":[[2012,9,11]]},"location":"Granada, Spain","end":{"date-parts":[[2012,9,14]]}},"container-title":["2012 IEEE Conference on Computational Intelligence and Games (CIG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6361518\/6374097\/06374141.pdf?arnumber=6374141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T00:08:10Z","timestamp":1562458090000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6374141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,9]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/cig.2012.6374141","relation":{},"subject":[],"published":{"date-parts":[[2012,9]]}}}