{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:41:53Z","timestamp":1742985713847,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540406662"},{"type":"electronic","value":"9783540451358"}],"license":[{"start":{"date-parts":[[2003,1,1]],"date-time":"2003-01-01T00:00:00Z","timestamp":1041379200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-45135-8_27","type":"book-chapter","created":{"date-parts":[[2010,6,22]],"date-time":"2010-06-22T17:59:26Z","timestamp":1277229566000},"page":"319-326","source":"Crossref","is-referenced-by-count":7,"title":["Reinforcement Learning in Large State Spaces"],"prefix":"10.1007","author":[{"given":"Karl","family":"Tuyls","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sam","family":"Maes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Manderick","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"27_CR1","unstructured":"Boutilier, C., Friedman, N., Goldszmidt, M., Koller, D.: Context-specific independence in Bayesian networks. In: Proc. UAI (1996)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)","DOI":"10.1016\/B978-0-08-051489-5.50008-4"},{"key":"27_CR3","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning in stochastic games (1999) (submitted for publication)"},{"key":"27_CR4","unstructured":"Kostiadis, K., Hu, H.: Reinforcement Learning and Co-operation in a Simulated Multi-agent System. In: Proc. of IEEE\/RJS IROS 1999, Korea (1999)"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Litmann, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Moore, A.W., Atkeson, C.: The Parti-game Algorithm for Variable Resolution Reinforcement Learning in Multidimensional State Space. Machine Learning Journal\u00a021 (1995)","DOI":"10.1007\/BF00993591"},{"key":"27_CR7","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1080\/088395198117848","volume":"12","author":"I. Noda","year":"1998","unstructured":"Noda, I., Matsubara, H., Hiraki, K., Frank, I.: Soccer Server: A Tool for Research om Multiagent Systems. Applied Artificial Intelligence\u00a012, 233\u2013250 (1998)","journal-title":"Applied Artificial Intelligence"},{"key":"27_CR8","unstructured":"Nowe, A., Verbeeck, K.: Learning Automata and Pareto Optimality for Coordination in MAS. Technical report, COMO, Vrije Universiteit Brussel (2000)"},{"key":"27_CR9","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)"},{"key":"27_CR10","unstructured":"Pyeatt, L.D., Howe, A.E.: Decision Tree Function Approximation in Reinforcement Learning. Technical Report CS-98-112, Colorado State University (1998)"},{"key":"27_CR11","series-title":"Series in Artificial Intelligence","volume-title":"Artificial Intelligence: a Modern Approach","author":"S. Russell","year":"1995","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: a Modern Approach. Series in Artificial Intelligence. Prentice Hall, Englewood Cliffs, New Jersey (1995)"},{"key":"27_CR12","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4151.001.0001","volume-title":"Layered Learning in Multiagent Systems. A Winning Approach to Robotic Soccer","author":"P. Stone","year":"2000","unstructured":"Stone, P.: Layered Learning in Multiagent Systems. A Winning Approach to Robotic Soccer. MIT Press, Cambridge (2000)"},{"key":"27_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2002: Robot Soccer World Cup VI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-45135-8_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T15:06:15Z","timestamp":1558278375000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-45135-8_27"}},"subtitle":["Simulated Robotic Soccer as a Testbed"],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540406662","9783540451358"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-45135-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}