{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:03:35Z","timestamp":1742936615949,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540726647"},{"type":"electronic","value":"9783540726654"}],"license":[{"start":{"date-parts":[[2007,1,1]],"date-time":"2007-01-01T00:00:00Z","timestamp":1167609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-72665-4_3","type":"book-chapter","created":{"date-parts":[[2007,6,21]],"date-time":"2007-06-21T20:22:09Z","timestamp":1182457329000},"page":"26-37","source":"Crossref","is-referenced-by-count":0,"title":["Competition and Coordination in Stochastic Games"],"prefix":"10.1007","author":[{"given":"Andriy","family":"Burkov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdeslam","family":"Boularias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brahim","family":"Chaib-draa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"3_CR1","volume-title":"Proceedings of the Eleventh International Conference on Machine Learning (ICML\u201994)","author":"M. Littman","year":"1994","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning (ICML\u201994), New Brunswick, NJ, Morgan Kaufmann, San Francisco (1994)"},{"issue":"2","key":"3_CR2","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(2), 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"issue":"2-3","key":"3_CR3","first-page":"385","volume":"20","author":"O. Gies","year":"2006","unstructured":"Gies, O., Chaib-draa, B.: Apprentissage de la coordination multiagent: une m\u00e9thode bas\u00e9e sur le Q-learning par jeu adaptatif. Revue d\u2019Intelligence Artificielle\u00a020(2-3), 385\u2013412 (2006)","journal-title":"Revue d\u2019Intelligence Artificielle"},{"key":"3_CR4","volume-title":"Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI\u201994)","author":"S. Singh","year":"1994","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 (UAI\u201994), Morgan Kaufmann, San Francisco (1994)"},{"key":"3_CR5","volume-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI\u201998)","author":"C. Claus","year":"1998","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI\u201998), AAAI Press, Menlo Park (1998)"},{"key":"3_CR6","volume-title":"Proceedings of the Fifteenth International Conference on Machine Learning (ICML\u201998)","author":"J. Hu","year":"1998","unstructured":"Hu, J., Wellman, P.: Multiagent reinforcement learning: Theoretical framework and an algorithm. In: Proceedings of the Fifteenth International Conference on Machine Learning (ICML\u201998), Morgan Kaufmann, San Francisco (1998)"},{"key":"3_CR7","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.: 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":"3_CR8","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning (ICML\u201901)","author":"M. Littman","year":"2001","unstructured":"Littman, M.: Friend-or-foe Q-learning in general-sum games. In: Proceedings of the Eighteenth International Conference on Machine Learning (ICML\u201901), Morgan Kaufmann, San Francisco (2001)"},{"key":"3_CR9","unstructured":"Chang, Y., Kaelbling, L.: Playing is believing: The role of beliefs in multi-agent learning. In: Proceedings of the Advances in Neural Information Processing Systems (NIPS\u201901), Canada (2001)"},{"key":"3_CR10","volume-title":"Advances in Neural Information Processing Systems","author":"G. Tesauro","year":"2004","unstructured":"Tesauro, G.: Extending Q-learning to general adaptive multi-agent systems. In: Thrun, S., Saul, L., Scholkopf, B. (eds.) Advances in Neural Information Processing Systems, vol.\u00a016, MIT Press, Cambridge (2004)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Burkov, A., Chaib-draa, B.: Effective learning in adaptive dynamic systems. In: Proceedings of the AAAI, Spring Symposium on Decision Theoretic and Game Theoretic Agents (GTDT\u201907), Stanford, California, To appear (2007)","DOI":"10.1145\/1329125.1329174"},{"issue":"1","key":"3_CR12","doi-asserted-by":"publisher","first-page":"57","DOI":"10.2307\/2951778","volume":"61","author":"H. Young","year":"1993","unstructured":"Young, H.: The evolution of conventions. Econometrica\u00a061(1), 57\u201384 (1993)","journal-title":"Econometrica"},{"issue":"3","key":"3_CR13","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"3_CR14","volume-title":"Advances in Neural Information Processing Systems","author":"R. Powers","year":"2005","unstructured":"Powers, R., Shoham, Y.: New criteria and a new algorithm for learning in multi-agent systems. In: Saul, L.K., Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol.\u00a017, MIT Press, Cambridge (2005)"},{"key":"3_CR15","unstructured":"Powers, R., Shoham, Y.: Learning against opponents with bounded memory. In: Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI\u201905 (2005)"}],"container-title":["Lecture Notes in Computer Science","Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-72665-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T09:42:55Z","timestamp":1558258975000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-72665-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540726647","9783540726654"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-72665-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}