{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T14:40:31Z","timestamp":1725892831960},"publisher-location":"Berlin, Heidelberg","reference-count":11,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540362975"},{"type":"electronic","value":"9783540362999"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11795131_94","type":"book-chapter","created":{"date-parts":[[2006,9,26]],"date-time":"2006-09-26T11:48:02Z","timestamp":1159271282000},"page":"643-650","source":"Crossref","is-referenced-by-count":0,"title":["Opponent Learning for Multi-agent System Simulation"],"prefix":"10.1007","author":[{"given":"Ji","family":"Wu","sequence":"first","affiliation":[]},{"given":"Chaoqun","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Shiyao","family":"Jin","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"94_CR1","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)"},{"key":"94_CR2","first-page":"279","volume":"3","author":"J.C.H. Christopher","year":"1992","unstructured":"Christopher, J.C.H., Watkins, Dayan, P.: Q-learnin. Machine learning\u00a03, 279\u2013292 (1992)","journal-title":"Machine learning"},{"key":"94_CR3","unstructured":"Bowling, M.: Multi-agent learning in the presence of agents with limitations, Ph.D. dissertation, School of Computer Science, Carnegie Mellon University, Pittsburgh (2003)"},{"key":"94_CR4","first-page":"157","volume-title":"Proceedings of ICML 1994","author":"M.L. Littman","year":"1994","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of ICML 1994, pp. 157\u2013163. Morgan Kaufmann, San Francisco (1994)"},{"key":"94_CR5","doi-asserted-by":"crossref","unstructured":"Suematsu, N., Hayashi, A.: A multi-agent reinforcement learning algorithm using extended optimal response. In: Proceedings of the 1st International Joint Conference on Autonomous Agents & Multi-agent Systems, Bologna, Italy, pp. 370\u2013377 (2002)","DOI":"10.1145\/544829.544831"},{"key":"94_CR6","unstructured":"Uther, W., Veloso, M.: Adversarial reinforcement learning, Technical Report, Carnegie Mellon University, Pittsburgh (1997)"},{"key":"94_CR7","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"94_CR8","first-page":"159","volume":"22","author":"S. Mahadevan","year":"1996","unstructured":"Mahadevan, S.: Average reward reinforcement learning: foundations, algorithms, and empirical results. Machine Learning\u00a022, 159\u2013195 (1996)","journal-title":"Machine Learning"},{"key":"94_CR9","unstructured":"Spronck, P., Kuyper, I.S., Postma, E.: Improving opponent intelligence through machine learning. In: Proceedings of the 14th Belgium-Netherlands Conference on AI, pp. 299\u2013306 (2002)"},{"key":"94_CR10","series-title":"Lecture Notes in Artificial Intelligence","volume-title":"RoboCup 2004: Robot Soccer World Cup VIII","author":"J. Wendler","year":"2005","unstructured":"Wendler, J.: Recognizing and predicting agent behavior with case based reasoning. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS (LNAI), vol.\u00a03276, Springer, Heidelberg (2005)"},{"key":"94_CR11","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-540-45135-8_7","volume-title":"RoboCup 2002: Robot Soccer World Cup VI","author":"U. Visser","year":"2003","unstructured":"Visser, U., Weland, H.G.: Using online learning to analyze the opponents behavior. In: Kaminka, G.A., Lima, P.U., Rojas, R. (eds.) RoboCup 2002. LNCS (LNAI), vol.\u00a02752, pp. 78\u201393. Springer, Heidelberg (2003)"}],"container-title":["Lecture Notes in Computer Science","Rough Sets and Knowledge Technology"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11795131_94.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T15:10:43Z","timestamp":1605625843000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11795131_94"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540362975","9783540362999"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/11795131_94","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}