{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T06:50:22Z","timestamp":1763535022708},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642106767"},{"type":"electronic","value":"9783642106774"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-10677-4_65","type":"book-chapter","created":{"date-parts":[[2009,12,14]],"date-time":"2009-12-14T22:12:56Z","timestamp":1260828776000},"page":"570-579","source":"Crossref","is-referenced-by-count":4,"title":["Learning Cooperative Behaviours in Multiagent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Somnuk","family":"Phon-Amnuaisuk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"6","key":"65_CR1","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/70.736776","volume":"14","author":"T. Balch","year":"1998","unstructured":"Balch, T., Arkin, R.C.: Behaviour-based formation control for multirobot teams. IEEE Transactions on Robotics and Automation\u00a014(6), 926\u2013939 (1998)","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"65_CR2","unstructured":"Bowling, M., Velosa, M.: An analysis of stochastic game theory for multiagent reinforcement learning. Technical report, Carnegie Mellon University (2000), http:\/\/www.cs.ualberta.ca\/~bowling\/papers\/00tr.pdf"},{"issue":"2","key":"65_CR3","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L. Bu\u015foniu","year":"2008","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., Schutter, B.D.: A comprehensive survey of multi-agent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews\u00a038(2), 156\u2013172 (2008)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C:Applications and Reviews"},{"key":"65_CR4","first-page":"1","volume":"4","author":"Y.U. Cao","year":"1997","unstructured":"Cao, Y.U., Fukunaga, A.S., Kahng, A.B.: Cooperative mobile robotics:Antecedents and directions. Autonomous Robotics\u00a04, 1\u201323 (1997)","journal-title":"Autonomous Robotics"},{"issue":"4","key":"65_CR5","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/S1672-6529(08)60179-1","volume":"5","author":"H.B. Duan","year":"2009","unstructured":"Duan, H.B., Ma, G.J., Luo, D.L.: Optimal formation reconfiguration control of multiple UCAVs using improved particle swarm optimisation. Bionic Engineering\u00a05(4), 340\u2013347 (2009)","journal-title":"Bionic Engineering"},{"key":"65_CR6","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1162\/jmlr.2003.4.6.1039","volume":"4","author":"J. Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. Journal of Machine Learning Research\u00a04, 1039\u20131069 (2003)","journal-title":"Journal of Machine Learning Research"},{"key":"65_CR7","doi-asserted-by":"publisher","first-page":"67","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, 67\u201379 (2001)","journal-title":"Journal of Cognitive Systems Research"},{"key":"65_CR8","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/A:1008819414322","volume":"4","author":"M.J. Matari\u0107","year":"1997","unstructured":"Matari\u0107, M.J.: Reinforcement learning in multi-robot domain. Autonomous Robots\u00a04, 73\u201383 (1997)","journal-title":"Autonomous Robots"},{"key":"65_CR9","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/S1389-0417(01)00017-1","volume":"2","author":"M.J. Matari\u0107","year":"2001","unstructured":"Matari\u0107, M.J.: Learning in behaviour-based multi-robot systems: policies, models, and other agents. Journal of Cognitive Systems Research\u00a02, 81\u201393 (2001)","journal-title":"Journal of Cognitive Systems Research"},{"key":"65_CR10","unstructured":"Morales, E.F.: Scaling up reinforcement learning with a relational representation. In: Workshops on Adaptability in Multi-Agent Systems, The First RoboCup Australian Open (AORC 2003), Sydney, Australia (January 31, 2003)"},{"key":"65_CR11","unstructured":"Morita, M., Ishikawa, M.: Brain-inspired emergence of behaviours based on the desire for existence by reinforcement learning. In: Proceedings of the 15th International Conference on Neural Information Processing (ICONIP 2008), Auckland, New Zealand (2008)"},{"issue":"3","key":"65_CR12","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems\u00a011(3), 387\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"65_CR13","unstructured":"Sen, S., Sekaran, M., Hale, J.: Learning to coordinate without sharing information. In: Proceedings of the 12th National Conference on Artificial Intelligence, pp. 426\u2013431 (1994)"},{"key":"65_CR14","unstructured":"Shoham, Y., Powers, R.: Multiagent reinforcement learning: A critical survey. Technical report, Standford University (2003), http:\/\/multiagent.stanford.edu\/papers\/MALearning_ACriticalSurvey_2003_0516.pdf"},{"key":"65_CR15","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, The MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"65_CR16","volume-title":"Multiagent Systems: Algorithmic, Game-theoretic, and Logical Foundations","author":"Y. Shoham","year":"2009","unstructured":"Shoham, Y., Layton-Brown, K.: Multiagent Systems: Algorithmic, Game-theoretic, and Logical Foundations. Cambridge University Press, Cambridge (2009)"},{"key":"65_CR17","first-page":"279","volume":"8","author":"C.J. Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"65_CR18","unstructured":"Yang, E.F., Gu, D.B.: Multiagent reinforcement learning for multi-robot systems: A survey. Technical report, The University of Essex (2004), http:\/\/cswww.essex.ac.uk\/technical-report\/2004\/cs"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-10677-4_65.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:33:26Z","timestamp":1606185206000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-10677-4_65"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642106767","9783642106774"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-10677-4_65","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}