{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:46:08Z","timestamp":1742993168863,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642239373"},{"type":"electronic","value":"9783642239380"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-23938-0_21","type":"book-chapter","created":{"date-parts":[[2011,9,11]],"date-time":"2011-09-11T20:40:55Z","timestamp":1315773655000},"page":"201-210","source":"Crossref","is-referenced-by-count":1,"title":["Evolving Equilibrium Policies for a Multiagent Reinforcement Learning Problem with State Attractors"],"prefix":"10.1007","author":[{"given":"Florin","family":"Leon","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"21_CR1","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":"21_CR2","first-page":"374","volume-title":"Activitiy Analysis of Production and Allocation, ch. XXIV","author":"G.W. Brown","year":"1951","unstructured":"Brown, G.W.: Iterative solutions of games by fictitious play. In: Koopmans, T.C. (ed.) Activitiy Analysis of Production and Allocation, ch. XXIV, pp. 374\u2013376. Wiley, Chichester (1951)"},{"key":"21_CR3","series-title":"SCI","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-642-14435-6_7","volume-title":"Innovations in Multi-Agent Systems and Applications","author":"L. Bu\u015foniu","year":"2010","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-Agent Reinforcement Learning: An Overview. In: Srinivasan, D., Jain, L. (eds.) Innovations in Multi-Agent Systems and Applications. SCI, vol.\u00a0310, pp. 183\u2013221. Springer, Heidelberg (2010)"},{"key":"21_CR4","unstructured":"Conitzer, V., Sandholm, T.: AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. In: Proceedings of the 20th International Conference on Machine Learning, ICML 2003, Washington, US, pp. 83\u201390 (2003)"},{"key":"21_CR5","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proceedings of the 15th International Conference on Machine Learning, ICML 1998, Madison, US, pp. 242\u2013250 (1998)"},{"key":"21_CR6","unstructured":"Leon, F.: Intelligent Agent Planning with Quasi-Determined States Using Inductive Learning, Bulletin of the Polytechnic Institute of Ia\u015fi, Romania, tome LVI (LX), section Automatic Control and Computer Science, fasc. 3, pp. 27\u201342 (2010)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the 11th International Conference on MachineLearning, ICML 1994, New Brunswick, US, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"issue":"1","key":"21_CR8","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/S1389-0417(01)00015-8","volume":"2","author":"M.L. Littman","year":"2001","unstructured":"Littman, M.L.: Value-function reinforcement learning in Markov games. Journal of Cognitive Systems Research\u00a02(1), 55\u201366 (2001)","journal-title":"Journal of Cognitive Systems Research"},{"key":"21_CR9","unstructured":"Moore, A.: Efficient Memory-Based Learning for Robot Control, Ph.D. Dissertation, University of Cambridge (1990)"},{"key":"21_CR10","volume-title":"Artificial Intelligence: A Modern Approach","author":"S.J. Russell","year":"2002","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2002)","edition":"2"},{"key":"21_CR11","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 (1998)"},{"issue":"3","key":"21_CR12","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"},{"key":"21_CR13","unstructured":"Vidal, J.M.: Fundamentals of Multiagent Systems with NetLogo Examples (2007), \n                    \n                      http:\/\/jmvidal.cse.sc.edu\/papers\/mas.pdf"},{"key":"21_CR14","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards, PhD Thesis, King\u2019s College, Cambridge University (1989)"},{"key":"21_CR15","unstructured":"Wikipedia, The Free Encyclopedia: Voronoi diagram (2011), \n                    \n                      http:\/\/en.wikipedia.org\/wiki\/Voronoi_diagram"}],"container-title":["Lecture Notes in Computer Science","Computational Collective Intelligence. Technologies and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23938-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,4,3]],"date-time":"2019-04-03T17:46:59Z","timestamp":1554313619000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23938-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642239373","9783642239380"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23938-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}