{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T13:54:52Z","timestamp":1725544492984},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540330530"},{"type":"electronic","value":"9783540330592"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"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":[[2006]]},"DOI":"10.1007\/11691839_5","type":"book-chapter","created":{"date-parts":[[2006,3,6]],"date-time":"2006-03-06T12:31:37Z","timestamp":1141648297000},"page":"100-114","source":"Crossref","is-referenced-by-count":0,"title":["Unifying Convergence and No-Regret in Multiagent Learning"],"prefix":"10.1007","author":[{"given":"Bikramjit","family":"Banerjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"5_CR1","first-page":"2","volume-title":"Proceedings of the 19th National Conference on Artificial Intelligence (AAAI 2004)","author":"B. Banerjee","year":"2004","unstructured":"Banerjee, B., Peng, J.: Performance bounded reinforcement learning in strategic intercations. In: Proceedings of the 19th National Conference on Artificial Intelligence (AAAI 2004), pp. 2\u20137. AAAI Press, San Jose (2004)"},{"unstructured":"Jafari, A., Greenwald, A., Gondek, D., Ercal, G.: On no-regret learning, fictitious play, and Nash equilibrium. In: Proceedings of the 18th International Conference on Machine Learning, pp. 216\u2013223 (2001)","key":"5_CR2"},{"key":"5_CR3","doi-asserted-by":"publisher","first-page":"286","DOI":"10.2307\/1969529","volume":"54","author":"J.F. Nash","year":"1951","unstructured":"Nash, J.F.: Non-cooperative games. Annals of Mathematics\u00a054, 286\u2013295 (1951)","journal-title":"Annals of Mathematics"},{"key":"5_CR4","first-page":"157","volume-title":"Proc. of the 11th Int. Conf. on Machine Learning","author":"M.L. Littman","year":"1994","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proc. of the 11th Int. Conf. on Machine Learning, pp. 157\u2013163. Morgan Kaufmann, San Mateo (1994)"},{"unstructured":"Littman, M., Szepesv\u00e1ri, C.: A generalized reinforcement learning model: Convergence and applications. In: Proceedings of the 13th International Conference on Machine Learning, pp. 310\u2013318 (1996)","key":"5_CR5"},{"key":"5_CR6","first-page":"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":"5_CR7","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learnig","author":"M.L. Littman","year":"2001","unstructured":"Littman, M.L.: Friend-or-foe Q-learning in general-sum games. In: Proceedings of the Eighteenth International Conference on Machine Learnig. Williams College, USA (2001)"},{"unstructured":"Greenwald, A., Hall, K.: Correlated Q-learning. In: Proceedings of AAAI Symposium on Collaborative Learning Agents (2002)","key":"5_CR8"},{"unstructured":"Singh, S., Kearns, M., Mansour, Y.: Nash convergence of gradient dynamics in general-sum games. In: Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, pp. 541\u2013548 (2000)","key":"5_CR9"},{"unstructured":"Bowling, M., Veloso, M.: Rational and convergent learning in stochastic games. In: Proceedings of the 17th International Joint Conference on Artificial Intelligence, Seattle,WA, pp. 1021\u20131026 (2001)","key":"5_CR10"},{"key":"5_CR11","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"},{"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 (2003)","key":"5_CR12"},{"key":"5_CR13","first-page":"322","volume-title":"Proceedings of the 36th Annual Symposium on Foundations of Compter Science, Milwaukee, WI","author":"P. Auer","year":"1995","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a rigged casino: The adversarial multi-arm bandit problem. In: Proceedings of the 36th Annual Symposium on Foundations of Compter Science, Milwaukee, WI, pp. 322\u2013331. IEEE Computer Society Press, Los Alamitos (1995)"},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1016\/0165-1889(94)00819-4","volume":"19","author":"D. Fudenberg","year":"1995","unstructured":"Fudenberg, D., Levine, D.K.: Consistency and cautious fictitious play. Journal of Economic Dynamics and Control\u00a019, 1065\u20131089 (1995)","journal-title":"Journal of Economic Dynamics and Control"},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1006\/game.1999.0738","volume":"29","author":"Y. Freund","year":"1999","unstructured":"Freund, Y., Schapire, R.E.: Adaptive game playing using multiplicative weights. Games and Economic Behavior\u00a029, 79\u2013103 (1999)","journal-title":"Games and Economic Behavior"},{"key":"5_CR16","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1006\/inco.1994.1009","volume":"108","author":"N. Littlestone","year":"1994","unstructured":"Littlestone, N., Warmuth, M.: The weighted majority algorithm. Information and Computation\u00a0108, 212\u2013261 (1994)","journal-title":"Information and Computation"},{"unstructured":"Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the 20th International Conference on Machine Learning, Washington, DC (2003)","key":"5_CR17"},{"unstructured":"Bowling, M.: Convergence and no-regret in multiagent learning. In: Proceedings of NIPS 2004\/5 (2005)","key":"5_CR18"},{"unstructured":"Powers, R., Shoham, Y.: New criteria and a new algorithm for learning in multi-agent systems. In: Proceedings of NIPS 2004\/5 (2005)","key":"5_CR19"},{"key":"5_CR20","first-page":"506","volume-title":"Proceedings of the 3rd International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"M. Weinberg","year":"2004","unstructured":"Weinberg, M., Rosenschein, J.S.: Best-response multiagent learning in non-stationary environments. In: Proceedings of the 3rd International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), vol.\u00a02, pp. 506\u2013513. ACM, New York (2004)"},{"unstructured":"Owen, G.: Game Theory. Academic Press, UK (1995)","key":"5_CR21"}],"container-title":["Lecture Notes in Computer Science","Learning and Adaption in Multi-Agent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11691839_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,25]],"date-time":"2019-01-25T16:11:03Z","timestamp":1548432663000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11691839_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540330530","9783540330592"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/11691839_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}