{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:29:50Z","timestamp":1780525790167,"version":"3.54.1"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2006,9,18]],"date-time":"2006-09-18T00:00:00Z","timestamp":1158537600000},"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\/s10994-006-0143-1","type":"journal-article","created":{"date-parts":[[2006,9,18]],"date-time":"2006-09-18T10:05:58Z","timestamp":1158573958000},"page":"23-43","source":"Crossref","is-referenced-by-count":73,"title":["AWESOME: A general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents"],"prefix":"10.1007","volume":"67","author":[{"given":"Vincent","family":"Conitzer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuomas","family":"Sandholm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2006,9,18]]},"reference":[{"key":"143_CR1","doi-asserted-by":"crossref","unstructured":"Auer, P., Cesa-Bianchi, N., Freund, Y., & Schapire, R. E. (1995). Gambling in a rigged casino: The adversarial multi-arm bandit problem. In Proceedings of the Annual Symposium on Foundations of Computer Science (FOCS) (pp. 322\u2013331).","DOI":"10.1109\/SFCS.1995.492488"},{"key":"143_CR2","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0304-4068(74)90037-8","volume":"1","author":"R. Aumann","year":"1974","unstructured":"Aumann, R. (1974). Subjectivity and correlation in randomized strategies. Journal of Mathematical Economics, 1, 67\u201396.","journal-title":"Journal of Mathematical Economics"},{"key":"143_CR3","unstructured":"Banerjee, B., & Peng, J. (2004). Performance bounded reinforcement learning in strategic interactions. In Proceedings of the National Conference on Artificial Intelligence (AAAI) (pp. 2\u20137). San Jose, CA, USA."},{"key":"143_CR4","unstructured":"Banerjee, B., Sen, S., & Peng, J. (2001). Fast concurrent reinforcement learners. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI) (pp. 825\u2013830). Seattle, WA."},{"key":"143_CR5","unstructured":"Bowling, M. (2005). Convergence and no-regret in multiagent learning. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) (pp. 209\u2013216). Vancouver, Canada."},{"key":"143_CR6","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","unstructured":"Bowling, M., & Veloso, M. (2002). Multiagent learning using a variable learning rate. Artificial Intelligence, 136, 215\u2013250.","journal-title":"Artificial Intelligence"},{"key":"143_CR7","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/S0004-3702(00)00039-4","volume":"121","author":"R. Brafman","year":"2000","unstructured":"Brafman, R., & Tennenholtz, M. (2000). A near-optimal polynomial time algorithm for learning in certain classes of stochastic games. Artificial Intelligence, 121, 31\u201347.","journal-title":"Artificial Intelligence"},{"key":"143_CR8","first-page":"213","volume":"3","author":"R. Brafman","year":"2003","unstructured":"Brafman, R., & Tennenholtz, M. (2003). R-max\u2014a general polynomial time algorithm for near-optimal reinforcement learning. Journal of Machine Learning Research, 3, 213\u2013231.","journal-title":"Journal of Machine Learning Research"},{"key":"143_CR9","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, 27\u201347.","journal-title":"Artificial Intelligence"},{"key":"143_CR10","unstructured":"Brafman, R., & Tennenholtz, M. (2005). Optimal efficient learning equilibrium: Imperfect monitoring in symmetric games. In Proceedings of the National Conference on Artificial Intelligence (AAAI) (pp. 726\u2013731). Pittsburgh, PA, USA."},{"key":"143_CR11","unstructured":"Cahn, A. (2000). General procedures leading to correlated equilibria Discussion paper 216, Center for Rationality, The Hebrew University of Jerusalem, Israel."},{"key":"143_CR12","unstructured":"Claus, C., & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems. In Proceedings of the National Conference on Artificial Intelligence (AAAI) (pp. 746\u2013752). Madison, WI."},{"key":"143_CR13","unstructured":"Conitzer, V., & Sandholm, T. (2003a). BL-WoLF: A framework for loss-bounded learnability in zero-sum games. In International Conference on Machine Learning (ICML) (pp. 91\u201398). Washington, DC, USA."},{"key":"143_CR14","unstructured":"Conitzer, V., & Sandholm, T. (2003b). Complexity results about Nash equilibria. In Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI) (pp. 765\u2013771). Acapulco, Mexico."},{"key":"143_CR15","doi-asserted-by":"crossref","unstructured":"Conitzer, V., & Sandholm, T. (2004). Communication complexity as a lower bound for learning in games. In International Conference on Machine Learning (ICML) (pp. 185\u2013192). Banff, Alberta, Canada.","DOI":"10.1145\/1015330.1015351"},{"key":"143_CR16","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1006\/game.1997.0595","volume":"21","author":"D. Foster","year":"1997","unstructured":"Foster, D., & Vohra, R. (1997). Calibrated learning and correlated equilibrium. Games and Economic Behavior, 21, 40\u201355.","journal-title":"Games and Economic Behavior"},{"key":"143_CR17","doi-asserted-by":"crossref","unstructured":"Foster, D. P., & Young, H. P. (2001). On the impossibility of predicting the behavior of rational agents. In Proceedings of the National Academy of Sciences, (Vol. 98, pp. 12848\u201312853).","DOI":"10.1073\/pnas.211534898"},{"key":"143_CR18","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1006\/game.1999.0738","volume":"29","author":"Y. Freund","year":"1999","unstructured":"Freund, Y., & Schapire, R. (1999). Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29, 79\u2013103.","journal-title":"Games and Economic Behavior"},{"key":"143_CR19","unstructured":"Fudenberg, D., & Levine, D. (1998). The theory of learning in games MIT Press."},{"key":"143_CR20","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1006\/game.1998.0705","volume":"29","author":"D. Fudenberg","year":"1999","unstructured":"Fudenberg, D., & Levine, D. (1999). Conditional universal consistency. Games and Economic Behavior, 29, 104\u2013130.","journal-title":"Games and Economic Behavior"},{"key":"143_CR21","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. K. (1995). Consistency and cautious fictitious play. Journal of Economic Dynamics and Control, 19, 1065\u20131089.","journal-title":"Journal of Economic Dynamics and Control"},{"key":"143_CR22","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/0899-8256(89)90006-7","volume":"1","author":"I. Gilboa","year":"1989","unstructured":"Gilboa, I., & Zemel, E. (1989). Nash and correlated equilibria: some complexity considerations. Games and Economic Behavior, 1, 80\u201393.","journal-title":"Games and Economic Behavior"},{"key":"143_CR23","unstructured":"Greenwald, A., & Hall, K. (2003). Correlated Q-learning. International Conference on Machine Learning (ICML) (pp. 242\u2013249). Washington, DC, USA."},{"key":"143_CR24","doi-asserted-by":"crossref","unstructured":"Greenwald, A., & Jafari, A. (2003). A general class of no-regret learning algorithms and game-theoretic equilibria. Conference on Learning Theory (COLT) Washington, DC.","DOI":"10.1007\/978-3-540-45167-9_2"},{"key":"143_CR25","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":"143_CR26","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1257\/000282803322655581","volume":"93","author":"S. Hart","year":"2003","unstructured":"Hart, S., & Mas-Colell, A. (2003). Uncoupled dynamics do not lead to Nash equilibrium. American Economic Review, 93, 1830\u20131836.","journal-title":"American Economic Review"},{"key":"143_CR27","unstructured":"Hu, J., & Wellman, M. P. (1998). Multiagent reinforcement learning: theoretical framework and an algorithm. International Conference on Machine Learning (ICML) (pp. 242\u2013250)."},{"key":"143_CR28","unstructured":"Jafari, A., Greenwald, A., Gondek, D., & Ercal, G. (2001). On no-regret learning, fictitious play, and Nash equilibrium. International Conference on Machine Learning (ICML) (pp. 226\u2013233). Williams College, MA, USA."},{"key":"143_CR29","doi-asserted-by":"crossref","unstructured":"Kakade, S., & Foster, D. (2004). Deterministic calibration and Nash equilibrium. In Conference on Learning Theory (COLT) Banff, Alberta, Canada.","DOI":"10.1007\/978-3-540-27819-1_3"},{"key":"143_CR30","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, 1019\u20131045.","journal-title":"Econometrica"},{"key":"143_CR31","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1137\/0112033","volume":"12","author":"C. Lemke","year":"1964","unstructured":"Lemke, C., & Howson, J. (1964). Equilibrium points of bimatrix games. Journal of the Society of Industrial and Applied Mathematics, 12, 413\u2013423.","journal-title":"Journal of the Society of Industrial and Applied Mathematics"},{"key":"143_CR32","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1006\/inco.1994.1009","volume":"108","author":"N. Littlestone","year":"1994","unstructured":"Littlestone, N., & Warmuth, M. K. (1994). The weighted majority algorithm. Information and Computation, 108, 212\u2013261.","journal-title":"Information and Computation"},{"key":"143_CR33","doi-asserted-by":"crossref","unstructured":"Littman, M. (1994). Markov games as a framework for multi-agent reinforcement learning. In International Conference on Machine Learning (ICML) (pp. 157\u2013163).","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"143_CR34","unstructured":"Littman, M. (2001). Friend or foe Q-learning in general-sum Markov games. In International Conference on Machine Learning (ICML) (pp. 322\u2013328)."},{"key":"143_CR35","doi-asserted-by":"crossref","unstructured":"Littman, M., & Stone, P. (2003). A polynomial-time Nash equilibrium algorithm for repeated games. In Proceedings of the ACM Conference on Electronic Commerce (ACM-EC) (pp. 48\u201354). San Diego, CA.","DOI":"10.1145\/779928.779935"},{"key":"143_CR36","unstructured":"Littman, M., & Szepesv\u00e1ri, C. (1996). A generalized reinforcement-learning model: convergence and applications. In International Conference on Machine Learning (ICML) (pp. 310\u2013318)."},{"key":"143_CR37","unstructured":"Miyasawa, K. (1961). On the convergence of the learning process in a 2 \u00d7 2 nonzero sum two-person game Research memo 33, Princeton University."},{"key":"143_CR38","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/BF01753708","volume":"19","author":"J. Nachbar","year":"1990","unstructured":"Nachbar, J. (1990). Evolutionary selection dynamics in games: Convergence and limit properties. International Journal of Game Theory, 19, 59\u201389.","journal-title":"International Journal of Game Theory"},{"key":"143_CR39","doi-asserted-by":"crossref","first-page":"275","DOI":"10.2307\/2171894","volume":"65","author":"J. Nachbar","year":"1997","unstructured":"Nachbar, J. (1997). Prediction, optimization, and learning in games. Econometrica, 65, 275\u2013309.","journal-title":"Econometrica"},{"key":"143_CR40","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/PL00007181","volume":"18","author":"J. Nachbar","year":"2001","unstructured":"Nachbar, J. (2001). Bayesian learning in repeated games of incomplete information. Social Choice and Welfare, 18, 303\u2013326.","journal-title":"Social Choice and Welfare"},{"key":"143_CR41","doi-asserted-by":"crossref","unstructured":"Nash, J. (1950). Equilibrium points in n-person games. In Proc. of the National Academy of Sciences, 36, 48\u201349.","DOI":"10.1073\/pnas.36.1.48"},{"key":"143_CR42","doi-asserted-by":"crossref","unstructured":"Papadimitriou, C. (2001). Algorithms, games and the Internet. In Proceedings of the Annual Symposium on Theory of Computing (STOC) (pp. 749\u2013753).","DOI":"10.1145\/380752.380883"},{"key":"143_CR43","unstructured":"Pivazyan, K., & Shoham, Y. (2002). Polynomial-time reinforcement learning of near-optimal policies. In Proceedings of the National Conference on Artificial Intelligence (AAAI) Edmonton, Canada."},{"key":"143_CR44","unstructured":"Porter, R., Nudelman, E., & Shoham, Y. (2004). Simple search methods for finding a Nash equilibrium. In Proceedings of the National Conference on Artificial Intelligence (AAAI) (pp. 664\u2013669). San Jose, CA, USA."},{"key":"143_CR45","unstructured":"Powers, R., & Shoham, Y. (2005a). Learning against opponents with bounded memory. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI) Edinburgh, UK."},{"key":"143_CR46","unstructured":"Powers, R., & Shoham, Y. (2005b). New criteria and a new algorithm for learning in multi-agent systems. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) Vancouver, Canada."},{"key":"143_CR47","doi-asserted-by":"crossref","first-page":"296","DOI":"10.2307\/1969530","volume":"54","author":"J. Robinson","year":"1951","unstructured":"Robinson, J. (1951). An iterative method of solving a game. Annals of Mathematics, 54, 296\u2013301.","journal-title":"Annals of Mathematics"},{"key":"143_CR48","doi-asserted-by":"crossref","unstructured":"Sandholm, T., & Crites, R. (1996). Multiagent reinforcement learning in the iterated prisoner\u2019s dilemma. Biosystems, 37, 147\u2013166. Special issue on the Prisoner\u2019s Dilemma.","DOI":"10.1016\/0303-2647(95)01551-5"},{"key":"143_CR49","unstructured":"Sandholm, T., Gilpin, A., & Conitzer, V. (2005). Mixed-integer programming methods for finding Nash equilibria. In Proceedings of the National Conference on Artificial Intelligence (AAAI) (pp. 495\u2013501). Pittsburgh, PA, USA."},{"key":"143_CR50","unstructured":"Sen, S., & Weiss, G. (1998). Learning in multiagent systems. In G. Weiss (Ed.), Multiagent systems: a modern introduction to distributed artificial intelligence (Chapter 6, pp. 259\u2013298). MIT Press."},{"key":"143_CR51","doi-asserted-by":"crossref","unstructured":"Shapley, L. S. (1964). Some topics in two-person games. In M. Drescher, L. S. Shapley & A. W. Tucker (Eds.), Advances in game theory Princeton University Press.","DOI":"10.1515\/9781400882014-002"},{"key":"143_CR52","unstructured":"Simon, H. A. (1982). Models of bounded rationality, vol. 2. MIT Press."},{"key":"143_CR53","unstructured":"Singh, S., Kearns, M., & Mansour, Y. (2000). Nash convergence of gradient dynamics in general-sum games. In Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI) (pp. 541\u2013548). Stanford, CA."},{"key":"143_CR54","unstructured":"Stimpson, J., Goodrich, M., & Walters, L. (2001). Satisficing and learning cooperation in the prisoner\u2019s dilemma. In Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence (IJCAI) (pp. 535\u2013540). Seattle, WA."},{"key":"143_CR55","doi-asserted-by":"crossref","unstructured":"Tan, M. (1993). Multi-agent reinforcement learning: independent vs. cooperative agents. In International Conference on Machine Learning (ICML) (pp. 330\u2013337).","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"143_CR56","unstructured":"Wang, X., & Sandholm, T. (2002). Reinforcement learning to play an optimal Nash equilibrium in team Markov games. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) Vancouver, Canada."},{"key":"143_CR57","unstructured":"Wang, X., & Sandholm, T. (2003). Learning near-Pareto-optimal conventions in polynomial time. In Proceedings of the Annual Conference on Neural Information Processing Systems (NIPS) Vancouver, Canada."},{"key":"143_CR58","unstructured":"Zinkevich, M. (2003). Online convex programming and generalized infinitesimal gradient ascent. In International Conference on Machine Learning (ICML) (pp. 928\u2013936). Washington, DC, USA."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-0143-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-006-0143-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-006-0143-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T21:40:20Z","timestamp":1559338820000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-006-0143-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,9,18]]},"references-count":58,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2007,5]]}},"alternative-id":["143"],"URL":"https:\/\/doi.org\/10.1007\/s10994-006-0143-1","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,9,18]]}}}