{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T19:07:24Z","timestamp":1748632044377},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540201212"},{"type":"electronic","value":"9783540398578"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-39857-8_6","type":"book-chapter","created":{"date-parts":[[2010,6,28]],"date-time":"2010-06-28T00:07:15Z","timestamp":1277683635000},"page":"35-46","source":"Crossref","is-referenced-by-count":0,"title":["Abalearn: A Risk-Sensitive Approach to Self-play Learning in Abalone"],"prefix":"10.1007","author":[{"given":"Pedro","family":"Campos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thibault","family":"Langlois","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"6_CR1","unstructured":"Aichholzer, O., Aurenhammer, F., Werner, T.: Algorithmic fun: Abalone. Technical report, Institut for Theoretical Computer Science, Graz University of Technology (2002)"},{"key":"6_CR2","first-page":"28","volume-title":"Proc. 15th International Conf. on Machine Learning","author":"J. Baxter","year":"1998","unstructured":"Baxter, J., Tridgell, A., Weaver, L.: Knightcap: a chess program that learns by combining TD(\u03bb) with game-tree search. In: Proc. 15th International Conf. on Machine Learning, pp. 28\u201336. Morgan Kaufmann, San Francisco (1998)"},{"issue":"3","key":"6_CR3","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1023\/A:1007634325138","volume":"40","author":"J. Baxter","year":"2000","unstructured":"Baxter, J., Tridgell, A., Weaver, L.: Learning to play chess using temporal differences. Machine Learning\u00a040(3), 243\u2013263 (2000)","journal-title":"Machine Learning"},{"issue":"1","key":"6_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0020-0255(99)00093-6","volume":"122","author":"D.F. Beal","year":"2000","unstructured":"Beal, D.F., Smith, M.C.: Temporal difference learning for heuristic search and game playing. Information Sciences\u00a0122(1), 3\u201321 (2000)","journal-title":"Information Sciences"},{"key":"6_CR5","unstructured":"Dahl, F.A.: Honte, a go-playing program using neural nets (1999)"},{"key":"6_CR6","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1093\/comjnl\/6.3.232","volume":"6","author":"D. Michie","year":"1963","unstructured":"Michie, D.: Experiments on the mechanization of game-learning \u2013 part i. characterization of the model and its parameters. The Computer Journal\u00a06, 232\u2013236 (1963)","journal-title":"The Computer Journal"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1023\/A:1017940631555","volume":"49","author":"O. Mihatsch","year":"2002","unstructured":"Mihatsch, O., Neuneier, R.: Risk-sensitive reinforcement learning. Machine Learning\u00a049, 267\u2013290 (2002)","journal-title":"Machine Learning"},{"issue":"1","key":"6_CR8","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1023\/A:1007417214905","volume":"32","author":"J.B. Pollack","year":"1998","unstructured":"Pollack, J.B., Blair, A.D.: Co-evolution in the successful learning of backgammon strategy. Machine Learning\u00a032(1), 225\u2013240 (1998)","journal-title":"Machine Learning"},{"issue":"3","key":"6_CR9","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1147\/rd.33.0210","volume":"3","author":"A. Samuel","year":"1959","unstructured":"Samuel, A.: Some studies in machine learning using the game of checkers. IBM Journal of Research and Development\u00a03(3), 211\u2013229 (1959)","journal-title":"IBM Journal of Research and Development"},{"key":"6_CR10","unstructured":"Schaeffer, J., Hlynka, M., Jussila, V.: Temporal difference learning applied to a high-performance game-playing program. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 529\u2013534 (2001)"},{"key":"6_CR11","volume-title":"Advances in Neural Information Processing Systems","author":"N. Schraudolph","year":"1994","unstructured":"Schraudolph, N., Dayan, P., Sejnowski, T.J.: Temporal difference learning of position evaluation in the game of go. In: Advances in Neural Information Processing Systems, vol.\u00a06, Morgan Kaufmann Publishers, Inc., San Francisco (1994)"},{"key":"6_CR12","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"6_CR13","volume-title":"Reinforcement Learning: An Introduction Reinforcement Reinforcement Learning: an Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction Reinforcement Reinforcement Learning: an Introduction, 1st edn. The MIT Press, Cambridge (1998)","edition":"1"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Tesauro, G.: Practical issues in temporal difference learning. In: Moody, J.E., Hanson, S.J., Lippmann, R.P. (eds.) Advances in Neural Information Processing Systems, vol.\u00a04 (1992)","DOI":"10.1007\/978-1-4615-3618-5_3"},{"key":"6_CR15","first-page":"19","volume-title":"Proceedings of the AAAI Fall Symposium on Intelligent Games: Planning and Learning","author":"G. Tesauro","year":"1993","unstructured":"Tesauro, G.: Td-gammon, a self-teaching backgammon program, achieves masterlevel play. In: Proceedings of the AAAI Fall Symposium on Intelligent Games: Planning and Learning, pp. 19\u201323. The AAAI Press, Menlo Park (1993)"},{"issue":"3","key":"6_CR16","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G. Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and td-gammon. Communications of the ACM\u00a038(3), 58\u201368 (1995)","journal-title":"Communications of the ACM"},{"issue":"3","key":"6_CR17","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007469231743","volume":"32","author":"G. Tesauro","year":"1998","unstructured":"Tesauro, G.: Comments on co-evolution in the successful learning of backgammon strategy. Machine Learning\u00a032(3), 41\u2013243 (1998)","journal-title":"Machine Learning"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(01)00110-2","volume":"134","author":"G. Tesauro","year":"2002","unstructured":"Tesauro, G.: Programming backgammon using self-teaching neural nets. Artificial Intelligence\u00a0134, 181\u2013199 (2002)","journal-title":"Artificial Intelligence"},{"key":"6_CR19","first-page":"1069","volume-title":"Advances in Neural Information Processing Systems 7","author":"S. Thrun","year":"1995","unstructured":"Thrun, S.: Learning to play the game of chess. In: Tesauro, G., Touretzky, D., Leen, T. (eds.) Advances in Neural Information Processing Systems 7, pp. 1069\u20131076. The MIT Press, Cambridge (1995)"},{"key":"6_CR20","unstructured":"Yoshioka, T., Ishii, S., Ito, M.: Strategy acquisition for the game othello based on reinforcement learning. IEICE Transactions on Inf. and Syst.\u00a012(E82 D) (December 1999)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning: ECML 2003"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-39857-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,15]],"date-time":"2019-03-15T00:18:24Z","timestamp":1552609104000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-39857-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540201212","9783540398578"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-39857-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}