{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T17:11:39Z","timestamp":1725729099614},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642386091"},{"type":"electronic","value":"9783642386107"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38610-7_36","type":"book-chapter","created":{"date-parts":[[2013,6,4]],"date-time":"2013-06-04T01:25:06Z","timestamp":1370309106000},"page":"385-396","source":"Crossref","is-referenced-by-count":1,"title":["Opponent Modelling by Sequence Prediction and Lookahead in Two-Player Games"],"prefix":"10.1007","author":[{"given":"Richard","family":"Mealing","sequence":"first","affiliation":[]},{"given":"Jonathan L.","family":"Shapiro","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"36_CR1","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. PhD thesis, Cambridge (1989)"},{"key":"36_CR2","unstructured":"Brown, G.: Iterative Solutions of Games by Fictitious Play. In: Activity Analysis of Production and Allocation. Wiley, New York (1951)"},{"key":"36_CR3","unstructured":"Carmel, Markovitch: Learning models of intelligent agents. In: Proc. of 13th Int. Conf. on AI, AAAI , pp. 62\u201367 (1996)"},{"key":"36_CR4","unstructured":"Jensen, B., Gini, S.: Non-stationary policy learning in 2-player zero sum games. In: Proc. of 20th Int. Conf. on AI, pp. 789\u2013794 (2005)"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Knoll, de Freitas: A machine learning perspective on predictive coding with paq. arXiv:1108.3298 (2011)","DOI":"10.1109\/DCC.2012.44"},{"key":"36_CR6","first-page":"337","volume":"116","author":"Faulkner Treisman","year":"1987","unstructured":"Treisman, Faulkner: Generation of random sequences by human subjects: Cognitive operations or psychological process? JEP: General 116, 337\u2013355 (1987)","journal-title":"JEP: General"},{"key":"36_CR7","unstructured":"Axelrod, R.: The evolution of strategies in the iterated prisoner\u2019s dilemma. In: Genetic Algorithms and Simulated Annealing, pp. 32\u201341. Morgan Kaufmann (1987)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: 11th Proc. of ICML, pp. 157\u2013163. Morgan Kaufmann (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Boytsov, Zaslavsky: Context Prediction in Pervasive Computing Systems. In: Burstein, F. (ed.) Supporting Real Time Decision-Making, pp. 35\u201363. Springer (2011)","DOI":"10.1007\/978-1-4419-7406-8_3"},{"key":"36_CR10","unstructured":"Lempel, Ziv: Compression of individual sequences via variable-rate coding (1978)"},{"key":"36_CR11","unstructured":"Knoll, B.: Text prediction and classification using string matching (2009)"},{"key":"36_CR12","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1109\/26.61469","volume":"38","author":"A. Moffat","year":"1990","unstructured":"Moffat, A.: Implementing the ppm data compression scheme. IEEE Transactions on Communications\u00a038, 1917\u20131921 (1990)","journal-title":"IEEE Transactions on Communications"},{"key":"36_CR13","unstructured":"Gopalratnam, K., Cook, D.J.: Activelezi: An incremental parsing algorithm for sequential prediction. In: 16th Int. FLAIRS Conf., pp. 38\u201342 (2003)"},{"key":"36_CR14","first-page":"43","volume":"15","author":"P. Laird","year":"1994","unstructured":"Laird, P., Saul, R.: Discrete sequence prediction and its applications. Machine Learning\u00a015, 43\u201368 (1994)","journal-title":"Machine Learning"},{"key":"36_CR15","unstructured":"Millington, I.: Learning. In: Artificial Intelligence for Games, pp. 583\u2013590. Morgan Kaufmann (2006)"},{"key":"36_CR16","first-page":"115","volume":"3","author":"F.A. Gers","year":"2002","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with lstm recurrent networks. JMLR\u00a03, 115\u2013143 (2002)","journal-title":"JMLR"},{"key":"36_CR17","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artificial Intelligence\u00a0136, 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"key":"36_CR18","unstructured":"Abdallah, S., Lesser, V.R.: Non-linear dynamics in multiagent reinforcement learning algorithms. In: AAMAS (3), pp. 1321\u20131324 (2008)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Lesser: Multi-agent learning with policy prediction. In: AAAI (2010)","DOI":"10.1609\/aaai.v24i1.7639"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Piccolo, E., Squillero, G.: Adaptive opponent modelling for the iterated prisoner\u2019s dilemma. In: IEEE CEC, pp. 836\u2013841 (2011)","DOI":"10.1109\/CEC.2011.5949705"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Soft Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38610-7_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,2]],"date-time":"2023-07-02T04:48:27Z","timestamp":1688273307000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-38610-7_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642386091","9783642386107"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38610-7_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}