{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:06:14Z","timestamp":1761894374970},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2006,8,16]],"date-time":"2006-08-16T00:00:00Z","timestamp":1155686400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2007,5]]},"DOI":"10.1007\/s10994-006-9643-2","type":"journal-article","created":{"date-parts":[[2006,9,4]],"date-time":"2006-09-04T12:47:53Z","timestamp":1157374073000},"page":"45-76","source":"Crossref","is-referenced-by-count":17,"title":["A general criterion and an algorithmic framework for learning in multi-agent systems"],"prefix":"10.1007","volume":"67","author":[{"given":"Rob","family":"Powers","sequence":"first","affiliation":[]},{"given":"Yoav","family":"Shoham","sequence":"additional","affiliation":[]},{"given":"Thuc","family":"Vu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2006,8,16]]},"reference":[{"key":"9643_CR1","volume-title":"The Evolution of Cooperation","author":"R. Axelrod","year":"1984","unstructured":"Axelrod, R. (1984). The Evolution of Cooperation. New York: Basic Books."},{"key":"9643_CR2","unstructured":"Banerjee, B., & Peng, J. (2005). Efficient no-regret multiagent learning. In Proceedings of the Twentieth National Conference on Artificial Intelligence, (pp. 41\u201346)."},{"key":"9643_CR3","unstructured":"Bowling, M. (2005). Convergence and no-regret in multiagent learning. In Advances in Neural Information Processing Systems 17, pp. 209\u2013216."},{"key":"9643_CR4","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002a","unstructured":"Bowling, M., & Veloso, M. (2002a). Multiagent learning using a variable learning rate. Artificial Intelligence, 136, 215\u2013250.","journal-title":"Artificial Intelligence"},{"key":"9643_CR5","unstructured":"Bowling, M., & Veloso, M.M. (2002b). Existence of multiagent equilibria with limited agents. Technical report CMU-CS-02-104, Computer Science Department, Carnegie Mellon University."},{"issue":"1\u20132","key":"9643_CR6","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.artint.2004.04.013","volume":"159","author":"R. Brafman","year":"2004","unstructured":"Brafman, R., & Tennenholtz, M. (2004). Efficient learning equilibrium. Artificial Intelligence, 159(1\u20132), 27\u201347.","journal-title":"Artificial Intelligence"},{"key":"9643_CR7","first-page":"374","volume-title":"Activity Analysis of Production and Allocation","author":"G. Brown","year":"1951","unstructured":"Brown, G. (1951). Iterative solution of games by fictitious play. In Activity Analysis of Production and Allocation (pp. 374\u2013376). New York: John Wiley and Sons."},{"key":"9643_CR8","doi-asserted-by":"crossref","unstructured":"Chang, Y.-H., & Kaelbling, L. (2005). Hedged learning: regret-minimization with learning experts. In Proceedings of the 22nd International Machine Learning Conference.","DOI":"10.1145\/1102351.1102367"},{"key":"9643_CR9","first-page":"1483","volume":"14","author":"Y.-H. Chang","year":"2002","unstructured":"Chang, Y.-H., & Kaelbling, L. P. (2002). Playing is believing: The role of beliefs in multi-agent learning. In Advances in Neural Information Processing Systems 14, (pp. 1483\u20131490).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"9643_CR10","unstructured":"Chrisman, L. (1992). Reinforcement learning with perceptual aliasing: the perceptual distinctions approach. In Proceedings of the Tenth National Conference on Artificial Intelligence, (pp. 183\u2013188)."},{"key":"9643_CR11","unstructured":"Claus, C., & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the Fifteenth National Conference on Artificial Intelligence, (pp. 746\u2013752)."},{"key":"9643_CR12","unstructured":"Conitzer, V., & Sandholm, T. (2003). Awesome: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. In Proceedings of the Twentieth International Conference on Machine Learning (pp. 83\u201390)."},{"key":"9643_CR13","unstructured":"de Farias, D. P., & Megiddo, N. (2004). How to combine expert (or novice) advice when actions impact the environment. In Advances in Neural Information Processing Systems 16."},{"key":"9643_CR14","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1006\/game.1999.0740","volume":"29","author":"D. Foster","year":"1999","unstructured":"Foster, D., & Vohra, R. (1999). Regret in the on-line decision problem. Games and Economic Behavior, 29, 7\u201336.","journal-title":"Games and Economic Behavior"},{"key":"9643_CR15","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1016\/0165-1889(94)00819-4","volume":"19","author":"D. Fudenberg","year":"1995","unstructured":"Fudenberg, D., & Levine, D. (1995). Universal consistency and cautious fictitious play. Journal of Economic Dynamics and Control, 19, 1065\u20131089.","journal-title":"Journal of Economic Dynamics and Control"},{"key":"9643_CR16","volume-title":"The Theory of Learning in Games","author":"D. Fudenberg","year":"1998","unstructured":"Fudenberg, D., & Levine, D. K. (1998). The Theory of Learning in Games Cambridge, MA: MIT Press."},{"key":"9643_CR17","first-page":"97","volume":"3","author":"J. F. Hannan","year":"1957","unstructured":"Hannan, J. F. (1957). Approximation to Bayes risk in repeated plays. Contributions to the Theory of Games, 3, 97\u2013139.","journal-title":"Contributions to the Theory of Games"},{"key":"9643_CR18","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1111\/1468-0262.00153","volume":"68","author":"S. Hart","year":"2000","unstructured":"Hart, S., & Mas-Colell, A. (2000). A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68, 1127\u20131150.","journal-title":"Econometrica"},{"key":"9643_CR19","unstructured":"Jafari, A., Greenwald, A., Gondek, D., & Ercal, G. (2001). On no-regret learning, fictitious play, and Nash equilibrium. In Proceedings of the Eighteenth International Conference on Machine Learning, (pp. 226\u2013223)."},{"issue":"5","key":"9643_CR20","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.2307\/2951492","volume":"61","author":"E. Kalai","year":"1993","unstructured":"Kalai, E., & Lehrer, E. (1993). Rational learning leads to Nash equilibrium. Econometrica, 61(5), 1019\u20131045.","journal-title":"Econometrica"},{"key":"9643_CR21","unstructured":"Littman, M., & Stone, P. (2001). Implicit negotiation in repeated games. In Proceedings of The Eighth International Workshop on Agent Theories, Architectures, and Languages, (pp. 393\u2013404)."},{"key":"9643_CR22","doi-asserted-by":"crossref","unstructured":"Mannor, S., & Shimkin, N. (2001). Adaptive strategies and regret minimization in arbitrarily varying markov environments. In Proceedings of the Fourtheenth Annual Conference on Computational Learning Theory (pp. 128\u2013142).","DOI":"10.1007\/3-540-44581-1_9"},{"key":"9643_CR23","unstructured":"McCracken, P., & Bowling, M. (2004). Safe strategies for agent modelling in games. In AAAI 2004 Symposium on Artificial Multi-Agent Learning [FS-04-02]. AAAI Press."},{"key":"9643_CR24","doi-asserted-by":"crossref","unstructured":"Neyman, A. (1985). Bounded complexity justifies cooperation in finitely repeated prisoner\u2019s dilemma. Economic Letters (pp. 227\u2013229).","DOI":"10.1016\/0165-1765(85)90026-6"},{"key":"9643_CR25","unstructured":"Nikovski, D., & Nourbakhsh, I. (2000). Learning probabilistic models for decision-theoretic navigation of mobile robots. In Proceedings of the International Conference on Machine Learning (pp. 266\u2013274)."},{"key":"9643_CR26","unstructured":"Nudelman, E., Wortman, J., Leyton-Brown, K., & Shoham, Y. (2004). Run the GAMUT: A comprehensive approach to evaluating game-theorectic algorithms. In Third International Joint Conference on Autonomous Agents and Multi Agent Systems."},{"key":"9643_CR27","doi-asserted-by":"crossref","unstructured":"Papadimitriou, C. H., & Yannakakis, M. (1994). On complexity as bounded rationality. In Proceedings of the Twenty-Sixth Annual ACM Symposium on Theory of Computing (pp. 726\u2013733).","DOI":"10.1145\/195058.195445"},{"key":"9643_CR28","unstructured":"Powers, R., & Shoham, Y. (2005). New criteria and a new algorithm for learning in multi-agent systems. In Advances in Neural Information Processing Systems 17. MIT Press."},{"key":"9643_CR29","unstructured":"Sen, S., & Weiss, G. (1998). Learning in multiagent systems. In Multiagent systems: a modern introduction to distributed artificial intelligence (pp. 259\u2013298). MIT Press."},{"key":"9643_CR30","unstructured":"Shoham, Y., Powers, R., & Grenager, T. (2004). On the agenda(s) of research on multi-agent learning. In AAAI 2004 Symposium on Artificial Multi-Agent Learning [FS-04-02]. AAAI Press."},{"key":"9643_CR31","unstructured":"Singh, S., Kearns, M., & Mansour, Y. (2000). Nash convergence of gradient dynamics in general-sum games. In Proceedings of the Seventeenth International Conference on Machine Learning (pp. 41\u201348)."},{"key":"9643_CR32","doi-asserted-by":"crossref","unstructured":"Stone, P., & Veloso, M. (2000). Multiagent systems: A survey from a machine learning perspective. Autonomous Robots, 8(3).","DOI":"10.1023\/A:1008942012299"},{"key":"9643_CR33","doi-asserted-by":"crossref","unstructured":"Watkins, C., & Dayan, P. (1992). Technical note: Q-learning. Machine Learning, 8( 3\/4), 279\u2013292.","DOI":"10.1023\/A:1022676722315"},{"key":"9643_CR34","unstructured":"Zinkevich, M. (2003). Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the Twentieth International Conference on Machine Learning."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-9643-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-006-9643-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-9643-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T01:40:22Z","timestamp":1559353222000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-006-9643-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,8,16]]},"references-count":34,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2007,5]]}},"alternative-id":["9643"],"URL":"https:\/\/doi.org\/10.1007\/s10994-006-9643-2","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,8,16]]}}}