{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T09:10:58Z","timestamp":1690967458544},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2015,1,31]],"date-time":"2015-01-31T00:00:00Z","timestamp":1422662400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann Math Artif Intell"],"published-print":{"date-parts":[[2015,4]]},"DOI":"10.1007\/s10472-015-9450-1","type":"journal-article","created":{"date-parts":[[2015,1,30]],"date-time":"2015-01-30T17:41:55Z","timestamp":1422639715000},"page":"335-358","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A unifying learning framework for building artificial game-playing agents"],"prefix":"10.1007","volume":"73","author":[{"given":"Wenlin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"David K.","family":"Levine","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,1,31]]},"reference":[{"key":"9450_CR1","unstructured":"Airiau, S., Endriss, U.: Multiagent resource allocation with sharable items: Simple protocols and nash equilibria In: Proceedings of the 9th International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS-2010) (2010)"},{"issue":"1","key":"9450_CR2","doi-asserted-by":"crossref","first-page":"121","DOI":"10.4086\/toc.2012.v008a006","volume":"8","author":"S Arora","year":"2012","unstructured":"Arora, S., Hazan, E., Kale, S.: The multiplicative weights update method: a meta-algorithm and applications. Theory Comput. 8(1), 121\u2013164 (2012)","journal-title":"Theory Comput."},{"key":"9450_CR3","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning. Springer-Verlag, New York, Inc. Secaucus, NJ (2006)"},{"issue":"10","key":"9450_CR4","doi-asserted-by":"crossref","first-page":"7280","DOI":"10.1073\/pnas.082080899","volume":"99","author":"E Bonabeau","year":"2002","unstructured":"Bonabeau, E.: Agent-Based Modeling: Methods and Techniques for Simulating Human Systems. Proc. Natl. Acad. Sci. U. S. A. 99(10), 7280\u20137287 (2002)","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"1\u20132","key":"9450_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0004-3702(97)00029-5","volume":"94","author":"C Boutilier","year":"1997","unstructured":"Boutilier, C., Shoham, Y., Wellman, M.P.: Economic principles of multi-agent systems. Artif. Intell. 94(1\u20132), 1\u20136 (1997)","journal-title":"Artif. Intell."},{"issue":"1","key":"9450_CR6","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1613\/jair.1332","volume":"22","author":"M Bowling","year":"2004","unstructured":"Bowling, M., Veloso, M.: Existence of multiagent equilibria with limited agents. J. Artif. Intell. Res. 22(1), 353\u2013384 (2004) http:\/\/dl.acm.org\/citation.cfm?id=1622487. 1622498","journal-title":"J. Artif. Intell. Res."},{"key":"9450_CR7","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1111\/1468-0262.00054","volume":"67","author":"C Camerer","year":"1999","unstructured":"Camerer, C., hua Ho, T.: Experience-weighted attraction learning in normal form games. Econometrica 67, 827\u2013874 (1999)","journal-title":"Econometrica"},{"issue":"3","key":"9450_CR8","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1162\/0033553041502225","volume":"119","author":"CF Camerer","year":"2004","unstructured":"Camerer, C.F., Ho, T.H., Chong, J.K.: A cognitive hierarchy model of games. Q. J. Econ. 119(3), 861\u2013898 (2004)","journal-title":"Q. J. Econ."},{"key":"9450_CR9","unstructured":"Carmel, D., Markovitch, S.: Learning models of intelligent agents. In: Proceedings of the Thirteenth National Conference on Artificial Intelligence pp 62\u201367 Portland Oregon (1996)"},{"key":"9450_CR10","unstructured":"Chen, Y., Lai, J., Parkes, D.C., Procaccia, A.D.: Truth, justice, and cake cutting. In: Fox, M., Poole, D. (eds.) AAAI 2010, Atlanta, Georgia, USA, July 11\u201315, 2010. AAAI Press (2010)"},{"key":"9450_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Vaughan, J.W.: A new understanding of prediction markets via no-regret learning In: Proceedings of he 11th ACM conference on Electronic commerce, EC \u201910 pp 189\u2013198. ACM, New York, NY (2010)","DOI":"10.1145\/1807342.1807372"},{"key":"9450_CR12","doi-asserted-by":"crossref","unstructured":"Crandall, J.W., Ahmed, A., Goodrich, M.A.: In: Burgard, W., Roth, D. (eds.) : Learning in repeated games with minimal information: The effects of learning bias. AAAI. AAAI Press (2011)","DOI":"10.1609\/aaai.v25i1.7871"},{"issue":"1","key":"9450_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J. Royal Statist. Soc. Series B (Methodological) 39(1), 1\u201338 (1977)","journal-title":"J. Royal Statist. Soc. Series B (Methodological)"},{"issue":"2","key":"9450_CR14","doi-asserted-by":"crossref","first-page":"e87619","DOI":"10.1371\/journal.pone.0087619","volume":"9","author":"M Devaine","year":"2014","unstructured":"Devaine, M., Hollard, G., Daunizeau, J.: Theory of mind: did evolution fool us. PloS. One. 9(2), e87619 (2014)","journal-title":"PloS. One."},{"key":"9450_CR15","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1023427023289","volume":"3","author":"JM Dimicco","year":"2003","unstructured":"Dimicco, J.M., Greenwald, A., Maes, P.: Learning curve: A simulation-based approach to dynamic pricing. J. Electron. Commer. Res. 3, 245\u2013276 (2003)","journal-title":"J. Electron. Commer. Res."},{"key":"9450_CR16","unstructured":"Doshi, P., Qu, X., Goodie, A., Young, D.: Modeling recursive reasoning by humans using empirically informed interactive pomdps In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1, AAMAS \u201910, pp.1223\u20131230. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2010)"},{"key":"9450_CR17","first-page":"162","volume-title":"Computing good nash equilibria in graphical games Proceedings of the 8th ACM conference on Electronic commerce, EC \u201907","author":"E Elkind","year":"2007","unstructured":"Elkind, E., Golberg, L.A., Goldberg, P.W.: Computing good nash equilibria in graphical games Proceedings of the 8th ACM conference on Electronic commerce, EC \u201907, pp 162\u2013171. ACM, New York, NY USA (2007)"},{"issue":"4","key":"9450_CR18","first-page":"9","volume":"31","author":"E Elkind","year":"2010","unstructured":"Elkind, E., Leyton-Brown, K.: Algorithmic game theory and artificial intelligence. Artif. Intell. Mag. 31(4), 9\u201312 (2010)","journal-title":"Artif. Intell. Mag."},{"key":"9450_CR19","doi-asserted-by":"crossref","unstructured":"Erev, I.: On surprise, change, and the effect of recent outcomes. Front. Psychol. 3(0) (2012)","DOI":"10.3389\/fpsyg.2012.00024"},{"issue":"1","key":"9450_CR20","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/S0167-2681(99)00028-1","volume":"39","author":"I Erev","year":"1999","unstructured":"Erev, I., Bereby-Meyer, Y., Roth, A.E.: The effect of adding a constant to all payoffs: experimental investigation, and implications for reinforcement learning models. J. Econ. Behav. & Organ. 39(1), 111\u2013128 (1999)","journal-title":"J. Econ. Behav. & Organ."},{"issue":"2","key":"9450_CR21","doi-asserted-by":"crossref","first-page":"117","DOI":"10.3390\/g1020117","volume":"1","author":"I Erev","year":"2010","unstructured":"Erev, I., Ert, E., Roth, A.E.: A choice prediction competition for market entry games: An introduction. Games 1(2), 117\u2013136 (2010). doi: 10.3390\/g1020117","journal-title":"Games"},{"key":"9450_CR22","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1002\/bdm.683","volume":"23","author":"I Erev","year":"2010","unstructured":"Erev, I., Ert, E., Roth, A.E., Haruvy, E., Herzog, S., Hau, R., Hertwig, R., Steward, T., West, R., Lebiere, C.: A choice prediction competition, for choices from experience and from description. J. Behav. Decis. Mak. 23, 15\u201347 (2010)","journal-title":"J. Behav. Decis. Mak."},{"issue":"1","key":"9450_CR23","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s00199-007-0214-y","volume":"33","author":"I Erev","year":"2007","unstructured":"Erev, I., Roth, A., Slonim, R., Barron, G.: Learning and equilibrium as useful approximations: Accuracy of prediction on randomly selected constant sum games. Econ. Theory 33(1), 29\u201351 (2007)","journal-title":"Econ. Theory"},{"issue":"4","key":"9450_CR24","first-page":"848","volume":"88","author":"I Erev","year":"1998","unstructured":"Erev, I., Roth, A.E.: Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria. Am. Econ. Rev. 88(4), 848\u201381 (1998)","journal-title":"Am. Econ. Rev."},{"issue":"3","key":"9450_CR25","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/S0169-2070(02)00023-7","volume":"18","author":"I Erev","year":"2002","unstructured":"Erev, I., Roth, A.E., Slonim, R.L., Barron, G.: Predictive value and the usefulness of game theoretic models. Int. J. Forecast. 18(3), 359\u2013368 (2002)","journal-title":"Int. J. Forecast."},{"key":"9450_CR26","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1002\/bdm.556","volume":"322","author":"E Ert","year":"2007","unstructured":"Ert, E., Erev, I.: Replicated alternatives and the role of confusion, chasing, and regret in decisions from experience. J. Behav. Decis. Mak. 322, 305\u2013322 (2007)","journal-title":"J. Behav. Decis. Mak."},{"key":"9450_CR27","unstructured":"Fudenberg, D., Levine, D.K.: The Theory of Learning in Games, MIT Press Books, vol. 1. The MIT Press (1998)"},{"issue":"1\u20132","key":"9450_CR28","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.K.: Conditional universal consistency. Games Econ. Behav. 29(1\u20132), 104\u2013130 (1999)","journal-title":"Games Econ. Behav."},{"issue":"1","key":"9450_CR29","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.jet.2005.12.008","volume":"133","author":"TH Ho","year":"2007","unstructured":"Ho, T.H., Camerer, C.F., Chong, J.K.: Self-tuning experience weighted attraction learning in games. J. Econ. Theory 133(1), 177\u2013198 (2007)","journal-title":"J. Econ. Theory"},{"key":"9450_CR30","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"9450_CR31","unstructured":"Jafari, A., Greenwald, A.R., Gondek, D., Ercal, G.: On no-regret learning, fictitious play, and nash equilibrium In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML \u201901, pp 226\u2013233. Morgan Kaufmann Publishers Inc., San Francisco, CA (2001)"},{"key":"9450_CR32","unstructured":"Kearns, M., Littman, M.L., Singh, S.: Graphical models for game theory In: Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence (2001)"},{"key":"9450_CR33","doi-asserted-by":"crossref","unstructured":"Kleinberg, R., Piliouras, G., Tardos, \u00c9.: Multiplicative updates outperform generic no-regret learning in congestion games In: Proceedings of the forty-first annual ACM symposium on Theory of computing (2009)","DOI":"10.1145\/1536414.1536487"},{"issue":"1","key":"9450_CR34","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0899-8256(02)00544-4","volume":"45","author":"D Koller","year":"2003","unstructured":"Koller, D., Milch, B.: Multi-agent influence diagrams for representing and solving games. Games Econ. Behav. 45(1), 181\u2013221 (2003)","journal-title":"Games Econ. Behav."},{"key":"9450_CR35","doi-asserted-by":"crossref","unstructured":"Levitt, S.D., List, J.A.: Field experiments in economics: The past, the present, and the future. NBER Workingc Papers 14356 National Bureau of Economic Research Inc (2008)","DOI":"10.3386\/w14356"},{"key":"9450_CR36","unstructured":"Ng, B., Boakye, K., Meyers, C., Wang, A.: Bayes-adaptive interactive pomdps AAAI (2012)"},{"key":"9450_CR37","volume-title":"Probabilistic reasoning in intelligent systems: networks of plausible inference","author":"J Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco, CA (1988)"},{"issue":"1","key":"9450_CR38","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1613\/jair.2523","volume":"33","author":"I Rezek","year":"2008","unstructured":"Rezek, I., Leslie, D.S., Reece, S., Roberts, S.J., Rogers, A., Dash, R.K., Jennings, N.R.: On similarities between inference in game theory and machine learning. J. Artif. Intell. Res. 33(1), 259\u2013283 (2008)","journal-title":"J. Artif. Intell. Res."},{"issue":"7","key":"9450_CR39","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/j.artint.2006.02.006","volume":"171","author":"Y Shoham","year":"2007","unstructured":"Shoham, Y., Powers, R., Grenager, T.: If multi-agent learning is the answer, what is the question?. Artif. Intell. 171(7), 365\u2013377 (2007). doi: 10.1016\/j.artint.2006.02.006","journal-title":"Artif. Intell."},{"key":"9450_CR40","volume-title":"Learning from delayed rewards","author":"CJCH Watkins","year":"1989","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge (1989)"},{"key":"9450_CR41","unstructured":"Waugh, K., Bagnell, D., Ziebart, B.D.: Computational rationalization: The inverse equilibrium problem. In: Proceedings of the 28th International Conference on Machine Learning, pp 1169\u20131176, New York, NY (2011)"},{"key":"9450_CR42","unstructured":"Wright, J.R., Leyton-Brown, K.: Behavioral game theoretic models: a bayesian framework for parameter analysis In; Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 2 (2012)"},{"key":"9450_CR43","unstructured":"Yang, R., Ordonez, F., Tambe, M.: Computing optimal strategy against quantal response in security games In: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 2 (2012)"}],"container-title":["Annals of Mathematics and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-015-9450-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10472-015-9450-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10472-015-9450-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T08:46:30Z","timestamp":1690965990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10472-015-9450-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,31]]},"references-count":43,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2015,4]]}},"alternative-id":["9450"],"URL":"https:\/\/doi.org\/10.1007\/s10472-015-9450-1","relation":{},"ISSN":["1012-2443","1573-7470"],"issn-type":[{"value":"1012-2443","type":"print"},{"value":"1573-7470","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,31]]}}}