{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:59:39Z","timestamp":1773719979265,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2005,9,12]],"date-time":"2005-09-12T00:00:00Z","timestamp":1126483200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2006,1]]},"DOI":"10.1007\/s10458-005-3783-9","type":"journal-article","created":{"date-parts":[[2005,9,19]],"date-time":"2005-09-19T10:18:46Z","timestamp":1127125126000},"page":"115-153","source":"Crossref","is-referenced-by-count":73,"title":["An Evolutionary Dynamical Analysis of Multi-Agent Learning in Iterated Games"],"prefix":"10.1007","volume":"12","author":[{"given":"Karl","family":"Tuyls","sequence":"first","affiliation":[]},{"given":"Pieter Jan \u2019T","family":"Hoen","sequence":"additional","affiliation":[]},{"given":"Bram","family":"Vanschoenwinkel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,9,12]]},"reference":[{"key":"3783_CR1","doi-asserted-by":"crossref","unstructured":"B. Banerjee and J. Peng, \u201cAdaptive poilcy gradient in multiagent learning,\u201d in Proceedings of the Third International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2003.","DOI":"10.1145\/860575.860686"},{"key":"3783_CR2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"A. Barto","year":"2003","journal-title":"Discrete-Event Syst. J."},{"key":"3783_CR3","unstructured":"A. L. C. Bazzan, A game-theoretic approach to coordination of traffic signal agents, PhD thesis, University of Karlsruhe, 1997."},{"key":"3783_CR4","doi-asserted-by":"crossref","unstructured":"R. Becker, S. Zilberstein, V. Lesser, and C. V. Goldman, \u201cTransition independent decentralized Markov decision problem,\u201d in Proceedings of the Third International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2003.","DOI":"10.1145\/860575.860583"},{"issue":"1","key":"3783_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/jeth.1997.2319","volume":"77","author":"T. B\u00f6rgers","year":"1997","journal-title":"J. Econ. Theory"},{"key":"3783_CR6","unstructured":"R. Boyd and P. J. Richerson, Culture and the Evolutionary Process, The University of Chicago Press, 1985."},{"key":"3783_CR7","first-page":"15","volume":"58","author":"R. R. Bush","year":"1951","journal-title":"The Psychol. Rev."},{"key":"3783_CR8","doi-asserted-by":"crossref","DOI":"10.1037\/14496-000","volume-title":"Stochastic Models for Learning","author":"R. R. Bush","year":"1955"},{"key":"3783_CR9","unstructured":"C. Claus and G. Boutilier, \u201cThe Dynamics of Reinforcement Learning in Cooperative Multi-Agent Systems,\u201d in Proceedings of the 15th International Conference on Artificial Intelligence, pp. 746\u2013752, 1998."},{"issue":"5","key":"3783_CR10","doi-asserted-by":"crossref","first-page":"239","DOI":"10.2307\/1882186","volume":"87","author":"J. G. Cross","year":"1973","journal-title":"Quart. J. Econ."},{"key":"3783_CR11","unstructured":"C. M. Gintis, Game Theory Evolving, Princeton University Press, 2000."},{"key":"3783_CR12","unstructured":"T. Grenager, and R. Powers, and Y. Shoham, \u201cDispersion games: general definitions and some specific learning results,\u201d in Proceedings of the Eighteenth National Conference on Artificial Intelligence AAAI 02, 2002."},{"key":"3783_CR13","unstructured":"C. Guestrin, D. Koller, C. Gearhart, and N. Kanodia, \u201cGeneralizing plans to new environments in relational MDPs,\u201d in International Joint Conference on Artificial Intelligence (IJCAI-03), 2003."},{"key":"3783_CR14","unstructured":"M. W. Hrisch and S. Smale, Differential Equation, Dynamical Systems and Linear Algebra, Academic Press, Inc 1974."},{"key":"3783_CR15","doi-asserted-by":"crossref","unstructured":"J. Hofbauer and K. Sigmund, Evolutionary Games and Population Dynamics, Cambridge University Press, 1998.","DOI":"10.1017\/CBO9781139173179"},{"key":"3783_CR16","unstructured":"J. Hu and M. P. Wellman, \u201cMultiagent reinforcement learning in stochastic games,\u201d in Internal Report from the Laboratory for Information and Decision Systems and the Operation Research Center, 1999."},{"key":"3783_CR17","doi-asserted-by":"crossref","unstructured":"P. Huang and K. Sycara, \u201cMulti-agent Learning in Extensive Games with complete information,\u201d in Proceedings of the Third International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2003.","DOI":"10.1145\/860575.860688"},{"key":"3783_CR18","unstructured":"C. Jafari, A. Greenwald, D. Gondek, a0nd G. Ercal, \u201cOn no-regret learning fictitious play and nash equilibrium,\u201d in Proceedings of the Eighteenth International Conference on Machine Learning (ICML), Cambridge University Press, pp. 223\u2013226, 2001."},{"key":"3783_CR19","doi-asserted-by":"crossref","unstructured":"H. Jung and M. Tambe, \u201cPerformance model for large scale multiagent systems\u201d in Proceedings of the Third International Conference Autonomous Agents and Multiagent Systems (AAMAS), 2003.","DOI":"10.1145\/860575.860623"},{"key":"3783_CR20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L. P. Kaelbling","year":"1996","journal-title":"J. Artif. Intell. Res."},{"key":"3783_CR21","unstructured":"M. Lauer and M. Riedmiller, \u201cAn algorithm for distributed reinforcement learning in cooperative multi-agent systems,\u201d in Proc. 17th International Conf. on Machine Learning Morgan Kaufmann: San Francisco, CA, pp. 535\u2013542, 2000."},{"key":"3783_CR22","doi-asserted-by":"crossref","unstructured":"M. L. Littman, \u201cMarkov games as a framework for multi-agent reinforcement learning,\u201d in Proceedings of the Eleventh International Conference on Machine Learning,\u201d Cambridge University Press, pp. 157\u2013163, 1994.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3783_CR23","doi-asserted-by":"crossref","unstructured":"J. Maynard Smith, Evolution and the Theory of the Games, Cambridge University Press, 1982.","DOI":"10.1017\/CBO9780511806292"},{"issue":"2","key":"3783_CR24","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/246015a0","volume":"146","author":"J. Maynard Smith","year":"1973","journal-title":"Nature"},{"issue":"5","key":"3783_CR25","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/TSMC.1974.5408453","volume":"14","author":"K. Narendra","year":"1974","journal-title":"IEEE Trans. Syst. Man Cybernet"},{"key":"3783_CR26","unstructured":"K. Narendra and M. Thathachar, Learning Automata: An Introduction, Prentice-Hall, 1989."},{"key":"3783_CR27","doi-asserted-by":"crossref","unstructured":"A. Now\u00e9, J. Parent, and K. Verbeeck, \u201cSocial agents playing a periodical policy,\u201d in Proceedings of the 12th European Conference on Machine Learning, Volume 2176 of Lecture Notes in Artificial Intelligence, Springer, pp. 382\u2013393, 2001.","DOI":"10.1007\/3-540-44795-4_33"},{"key":"3783_CR28","unstructured":"E. Nudelman, J. Wortman, K. Leyton-Brown, and Y. Shoham, \u201cRun the GAMUT: A comprehensive approach to evaluating game-theoretic algorithms, algorithms,\u201d in Proceedings of the Fourth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2004."},{"key":"3783_CR29","unstructured":"M. J. Osborne and A. Rubinstein, A Coruse in Game Theory, MIT Press, 1994."},{"key":"3783_CR30","doi-asserted-by":"crossref","unstructured":"J. Parent, K. Verbeeck, A. Now\u00e9, K. Steenhaut, J. Lemeire, and E. Dirkx, \u201cAdaptive load balancing of parallel applications with social reinforement learning on heterogeneous sysems,\u201d J. Sci. Program. 2004. to appear.","DOI":"10.1155\/2004\/987356"},{"key":"3783_CR31","unstructured":"S. Phelps, S. Parsons, and P. McBurney, \u201cAn evolutionary game-theoretic comparison of two double-action market designs,\u201d in Workshop on Agent Medicated Electronic commerce VI: Theories for Engineering of Distributed Mechanisms and Systems (AMEC\u201904), Volume 2531 of Lecture Notes in Artificial Intelligence, Springer, pp. 109\u2013118, 2004."},{"key":"3783_CR32","unstructured":"R. Powers and Y. Shoham, \u201cNew criteria and a new algorithm for learning in multi-agent system,\u201d in Proceedings of Eighteenth Annual Conference on Neural Information Processing Systems (NIPS), 2004."},{"key":"3783_CR33","unstructured":"F.V. Redondo, Game Theory and Economics, Cambridge University Press, 2001."},{"key":"3783_CR34","volume-title":"Evolutionary Games and Equilibrium Selection","author":"L. Samuelson","year":"1997"},{"issue":"14","key":"3783_CR35","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.1093\/nar\/28.14.2794","volume":"28","author":"T. D. Schneider","year":"2000","journal-title":"J. Nucl. Acid Res."},{"key":"3783_CR36","volume-title":"Life Love and Death: Models of Biological Reproduction and Aging","author":"D. Stauffer","year":"1999"},{"key":"3783_CR37","volume-title":"Reinforcement Learning: An Introduction","author":"R. S. Sutton","year":"1998"},{"key":"3783_CR38","doi-asserted-by":"crossref","unstructured":"P. J. \u2019t Hoen and S. M. Bohte, \u201cCOllective INtelligence with sequence of actions,\u201d in 14th European conference on Machine Learning, Volume 2837 of Lecture Notes in Articifical Intelligence, Springer, 2003.","DOI":"10.1007\/978-3-540-39857-8_18"},{"key":"3783_CR39","unstructured":"P. J. \u2019t Hoen and S. M. Bohte, \u201cCOllective INtelligence with task assignment,\u201d in proceedings of the Workshop on Collectives and the Design of Complex Systems (CDOCS03), forthcoming. Also available as Technical Rapport SEN-E0315, Lecture Notes in Artificial Intelligence, Springer, 2003."},{"key":"3783_CR40","doi-asserted-by":"crossref","unstructured":"P. J. \u2019t Hoen and K. Tuyls, \u201cAnalyzing multi-agent reinforcement learning using evolutionary dynamics,\u201d in Proceedings of the 15th European Conference on Machine Learning (ECML), Lecture Notes in Artificial Intelligence, Springer, 2004.","DOI":"10.1007\/978-3-540-30115-8_18"},{"issue":"6","key":"3783_CR41","first-page":"323","volume":"32","author":"P. S. Sastry","year":"2002","journal-title":"IEEE Trans. Sys. Man Cybernet"},{"key":"3783_CR42","first-page":"185","volume":"16","author":"J. N. Tsitsiklis","year":"1994","journal-title":"Machine Learn"},{"key":"3783_CR43","unstructured":"K. Tumer and D. Wolpert, \u201cCOllective INtelligence and Braess\u2019 Paradox,\u201d in Proceedings of the Sixteenth National Conference on Artificial Intelligence, Austin, pp. 104\u2013109, August, 2000."},{"key":"3783_CR44","volume-title":"Learning in Multi-Agent Systems, An Evolutionary Game Theoretic Approach","author":"K. Tuyls","year":"2004"},{"key":"3783_CR45","doi-asserted-by":"crossref","unstructured":"K. Tuyls, D. Heytens, A. Now\u00e9, and B. Manderick, \u201cExtended Replicator Dynamics as a Key to Reinforcement Learning in Multi-Agent Systems,\u201d in Proceedings of the 14th European Conference on Machine Learning (ECML), Volume 2837, of Lecture Notes in Artificial Intelligence, Springer, 2003.","DOI":"10.1007\/978-3-540-39857-8_38"},{"key":"3783_CR46","unstructured":"K. Tuyls, T. Lenaerts, K. Verbeeck, S. Maes and B. Manderick, \u201cTowards a relation between learning agents and evolutionary dynamics\u201d, in Proceedings of the Belgian-Dutch Conference on Artificial Intelligence (BNAIC 2002), Cambridge University Press, pp. 223\u2013226, 2002."},{"key":"3783_CR47","doi-asserted-by":"crossref","unstructured":"K. Tuyls, A. Nowe, T. Lenaerts, and B. Manderick, \u201cAn evolutionary game theoretic perspective on learning in multi-agent systems,\u201d in Synthese, Section Knowledge, Rationality and Action, Kluwer Academic Publishers, 2004, vol. 139, no. 2, pp. 297\u2013330.","DOI":"10.1023\/B:SYNT.0000024908.89191.f1"},{"key":"3783_CR48","doi-asserted-by":"crossref","unstructured":"K. Tuyls, K. Verbeeck, T. Lenaerts, \u201cA Selection-Mutation model for Q-learning in Multi-Agent Systems,\u201d in Proceedings of the Third Interational conference on Autonomous Agents and Multiagent Systems (AAMAS), The ACM International Conference Proceedings Series, 2003.","DOI":"10.1145\/860575.860687"},{"key":"3783_CR49","unstructured":"K. Verbeeck, A. Now\u00e9, and J. Parent, \u201cHomo egualis reinforcement learning agents for load balancing,\u201d in Proceedings of the 1st NASA Workshop on Radical Agent Concepts, Volume 2564 of Lecture Notes in Artificial Intelligence, Springer, pp. 109\u2013118, 2002."},{"key":"3783_CR50","unstructured":"J. von Neumann and O. Morgenstern, Theory of Games and Economic Behavior, Princeton University Press, 1944."},{"key":"3783_CR51","unstructured":"W. E. Walsh, R. Das, G. Tesauro, and J. O. Kephart, \u201cAnalyzing complex strategic interactions in multi-agent games,\u201d in Proceedings of the The Eighteenth National Conference on Artificial Intelligence (AAAI-02) Workshop on Game Theoretic and Decision Theoretic Agents, Lecture Notes in Artificial Intelligence, Springer, pp. 109\u2013118, 2002."},{"key":"3783_CR52","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","journal-title":"Machine Learn."},{"key":"3783_CR53","unstructured":"J. W. Weibull, Evolutionary Game Theory, MIT Press, 1996."},{"key":"3783_CR54","unstructured":"David H. Wolpert, Kagan Tumer, and Jeremy Frank, \u201cUsing COllective INtelligence to route internet traffic,\u201d in Advances in Neural Information Processing Systems-11, Denver, pp. 952\u2013958, 1998."},{"key":"3783_CR55","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1145\/301136.301167","volume-title":"Proceedings of the Third International Conference on Autonomous Agents (Agents\u201999).","author":"David H. Wolpert","year":"1999"}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-005-3783-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-005-3783-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-005-3783-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,4]],"date-time":"2025-01-04T10:34:29Z","timestamp":1735986869000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-005-3783-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,9,12]]},"references-count":55,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,1]]}},"alternative-id":["3783"],"URL":"https:\/\/doi.org\/10.1007\/s10458-005-3783-9","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,9,12]]}}}