{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T06:46:11Z","timestamp":1760424371844,"version":"3.41.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[1998,11,1]],"date-time":"1998-11-01T00:00:00Z","timestamp":909878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1998,11,1]],"date-time":"1998-11-01T00:00:00Z","timestamp":909878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1998,11]]},"DOI":"10.1023\/a:1007514623589","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:04:10Z","timestamp":1040533450000},"page":"179-200","update-policy":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["Conjectural Equilibrium in Multiagent Learning"],"prefix":"10.1007","volume":"33","author":[{"given":"Michael P.","family":"Wellman","sequence":"first","affiliation":[]},{"given":"Junling","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"186718_CR1","doi-asserted-by":"crossref","first-page":"225","DOI":"10.2307\/1927286","volume":"43","author":"K.J. Arrow","year":"1961","unstructured":"K.J. Arrow, H. B. Chenery, B. S. Minhas, & R. M. Solow. (1961). Capital-labor substitution andeconomic efficiency. Review of Economics and Statistics, 43, 225\u2013250.","journal-title":"Review of Economics and Statistics"},{"key":"186718_CR2","unstructured":"Boutilier, C. (1996). Learningconventions in multiagent stochastic domains using likelihood estimates. Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence, (pp. 106\u2013114). Portland, OR."},{"key":"186718_CR3","doi-asserted-by":"crossref","first-page":"188","DOI":"10.2307\/3145811","volume":"61","author":"K. Boyle","year":"1985","unstructured":"Boyle, K. (1985). Starting point bias in contingent valuation biddinggames. Land Economics, 61, 188\u2013194.","journal-title":"Land Economics"},{"issue":"4","key":"186718_CR4","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1257\/jep.6.4.83","volume":"6","author":"A. Brandenburger","year":"1992","unstructured":"Brandenburger, A. (1992). Knowledge and equilibrium in games.Journal of Economic Perspectives, 6(4), 83\u2013101.","journal-title":"Journal of Economic Perspectives"},{"issue":"1","key":"186718_CR5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1023\/A:1008654125853","volume":"12","author":"J.Q. Cheng","year":"1998","unstructured":"Cheng, J.Q. & Wellman, M.P. (1998). The WALRASalgorithm: A convergent distributed implementation of general equilibrium outcomes. Computational Economics, 12(1), 1\u201324.","journal-title":"Computational Economics"},{"key":"186718_CR6","unstructured":"Claus, C. & Boutilier, C. (1998). The dynamics of reinforcement learning in cooperative multiagent systems.Proceedings of the National Conference on Artificial Intelligence, (pp. 746\u2013752). Madison, WI."},{"key":"186718_CR7","unstructured":"Cliff, D. (1998).Evolving parameter sets for adaptive trading agents in continuous double-auction markets. Agents-98 Workshop on Artificial Societies and Computational Markets, (pp. 38\u201347). Minneapolis, MN."},{"key":"186718_CR8","doi-asserted-by":"crossref","unstructured":"Filar, J. & Vrieze, K. (1997). Competitive MarkovDecision Processes. Springer-Verlag.","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"186718_CR9","doi-asserted-by":"crossref","first-page":"523","DOI":"10.2307\/2951716","volume":"61","author":"D. Fudenberg","year":"1993","unstructured":"Fudenberg, D. & Levine, D.K. (1993). Self-confirming equilibrium.Econometrica, 61, 523\u2013545.","journal-title":"Econometrica"},{"key":"186718_CR10","unstructured":"Fudenberg, D. & Tirole, J. (1991). Game Theory. MIT Press."},{"key":"186718_CR11","doi-asserted-by":"crossref","unstructured":"Gibbons, R.(1992). Game Theory for Applied Economists. Princeton University Press.","DOI":"10.1515\/9781400835881"},{"key":"186718_CR12","doi-asserted-by":"crossref","first-page":"859","DOI":"10.2307\/2938230","volume":"59","author":"I. Gilboa","year":"1991","unstructured":"Gilboa, I. & Akihiko, M. (1991). Social stabilityand equilibrium. Econometrica, 59, 859\u2013867.","journal-title":"Econometrica"},{"key":"186718_CR13","unstructured":"Grefenstette, J.J., et al. (Eds.). (1996). AAAI Spring Symposium onAdaptation, Coevolution, and Learning in Multiagent Systems. AAAI Press."},{"key":"186718_CR14","doi-asserted-by":"crossref","first-page":"210","DOI":"10.2307\/3439508","volume":"79","author":"F.H. Hahn","year":"1977","unstructured":"Hahn, F.H. (1977). Exercises in conjecturalequilibrium analysis. Scandinavian Journal of Economics, 79, 210\u2013226.","journal-title":"Scandinavian Journal of Economics"},{"key":"186718_CR15","doi-asserted-by":"crossref","unstructured":"Horst, R., Pardalos, P. & Thoai, N.(1995). Introduction to Global Optimization. Kluwer Academic Publishers.","DOI":"10.1007\/978-1-4615-2025-2"},{"key":"186718_CR16","unstructured":"Hu, J & Wellman, M.P. (1996). Self-fulfillingbias in multiagent learning. Second International Conference on Multiagent Systems, (pp. 118\u2013125). Kyoto, Japan."},{"key":"186718_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J & Wellman, M.P. (1998a). Online learning about other agents in a dynamic multiagent system. Second International Conference on Autonomous Agents, pages 239\u2013246, Minneapolis.","DOI":"10.1145\/280765.280839"},{"key":"186718_CR18","unstructured":"Hu, J & Wellman, M.P. (1998b). Multiagentreinforcement learning: Theoretical framework and an algorithm. Fifteenth International Conference on Machine Learning, (pp. 242\u2013250). Madison, WI."},{"key":"186718_CR19","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L. & Moore, A.W. (1996). Reinforcement learning: A survey.Journal of Artificial Intelligence Research, 4, 237\u2013285.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"186718_CR20","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1103\/PhysRevA.40.404","volume":"40","author":"J.O. Kephart","year":"1989","unstructured":"Kephart, J.O., Hogg, T. & Huberman, B.A. (1989).Dynamics of computational ecosystems. Physical Review A, 40, 404\u2013421.","journal-title":"Physical Review A"},{"key":"186718_CR21","doi-asserted-by":"crossref","unstructured":"Littman, M.L. (1994). Markovgames as a framework for multi-agent reinforcement learning. Eleventh International Conference on Machine Learning, (pp. 157\u2013163).","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"186718_CR22","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/0899-8256(91)90006-Z","volume":"3","author":"P Milgrom","year":"1991","unstructured":"Milgrom, P & Roberts, J. (1991). Adaptive and sophisticated learning in normal form games. Games andEconomic Behavior, 3, 82\u2013100.","journal-title":"Games andEconomic Behavior"},{"key":"186718_CR23","unstructured":"Mullen, T. & Wellman, M.P. (1995). A simple computational market for networkinformation services. First International Conference on Multiagent Systems, (pp. 283\u2013289). San Francisco, CA."},{"key":"186718_CR24","doi-asserted-by":"crossref","first-page":"635","DOI":"10.2307\/1909319","volume":"30","author":"T. Negishi","year":"1962","unstructured":"Negishi, T. (1962). The stability of a competitive economy: A survey article. Econometrica, 30, 635\u2013669.","journal-title":"Econometrica"},{"key":"186718_CR25","unstructured":"Ono, N. & Fukumoto, K. (1996). Multi-agent reinforcement learning: A modular approach. Second International Conference on Multiagent Systems, (pp. 252\u2013258). Kyoto, Japan."},{"key":"186718_CR26","unstructured":"Russell, S. & Norvig, P. (1995). Artificial Intelligence:A Modern Approach. Prentice Hall."},{"key":"186718_CR27","first-page":"32","volume":"10","author":"K. Samples","year":"1985","unstructured":"Samples, K. (1985). A note on the existence of starting point bias in iterative biddinggames. Western Journal of Agricultural Economics, 10, 32\u201340.","journal-title":"Western Journal of Agricultural Economics"},{"key":"186718_CR28","unstructured":"Sandholm, T. & Ygge, F. (1997). On the gainsand losses of speculation in equilibrium markets. Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, (pp. 632\u2013638). Nagoya, Japan."},{"issue":"1","key":"186718_CR29","first-page":"87","volume":"17","author":"S. Sen","year":"1996","unstructured":"Sen, S. (1996). IJCAI-95 Workshop on Adaptation and Learning inMultiagent Systems. AI Magazine, 17(1), 87\u201389.","journal-title":"AI Magazine"},{"key":"186718_CR30","unstructured":"Sen, S. (Ed.). (1997). AAAI-97 Workshop on MultiagentLearning. AAAI Press."},{"key":"186718_CR31","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/S0004-3702(97)00028-3","volume":"94","author":"Y. Shoham","year":"1997","unstructured":"Shoham, Y. & Tennenholtz, M. (1997). On the emergence of social conventions: Modeling, analysis,and simulations. Artificial Intelligence, 94, 139\u2013166.","journal-title":"Artificial Intelligence"},{"key":"186718_CR32","unstructured":"Shoven, J.B. & Whalley, J. (1992). Applying GeneralEquilibrium. Cambridge University Press."},{"key":"186718_CR33","unstructured":"Spivak, B. (1965). Calculus on Manifolds. Benjamin\/Cummings."},{"key":"186718_CR34","unstructured":"Takayama, A.(1985). Mathematical Economics. Cambridge University Press."},{"key":"186718_CR35","volume-title":"Proceedings of the Tenth International Conference on Machine Learning","author":"M. Tan","year":"1993","unstructured":"Tan, M. (1993). Multi-agent reinforcement learning:Independent vs. cooperative agents. Proceedings of the Tenth International Conference on Machine Learning. Amherst, MA: Morgan Kaufmann."},{"key":"186718_CR36","unstructured":"Vidal, J.M. & Durfee, E.H. (1997). Agents learning about agents: A framework and analysis. InSen (Sen, 1997)."},{"issue":"3","key":"186718_CR37","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1080\/095281398146770","volume":"10","author":"J.M. Vidal","year":"1998","unstructured":"Vidal, J.M. & Durfee, E.H. (1998). Learning nested agent models in an information economy. Journal ofExperimental and Theoretical Artificial Intelligence, 10(3), 291\u2013308.","journal-title":"Journal ofExperimental and Theoretical Artificial Intelligence"},{"key":"186718_CR38","unstructured":"Wei\u00df, G. (1993). Learning to coordinateactions in multi-agent systems. Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, (pp. 311\u2013316)."},{"key":"186718_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.2","volume":"1","author":"M.P. Wellman","year":"1993","unstructured":"Wellman, M.P. (1993). A market-oriented programming environment and its application to distributedmulticommodity flow problems. Journal of Artificial Intelligence Research, 1, 1\u201323.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"186718_CR40","first-page":"125","volume":"9","author":"M.P. Wellman","year":"1995","unstructured":"Wellman, M.P. (1995). Acomputational market model for distributed configuration design. AI EDAM, 9, 125\u2013133.","journal-title":"AI EDAM"},{"issue":"2","key":"186718_CR41","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1257\/jep.10.2.105","volume":"10","author":"H.P. Young","year":"1996","unstructured":"Young, H.P. (1996).The economics of convention. Journal of Economic Perspectives, 10(2), 105\u2013122.","journal-title":"Journal of Economic Perspectives"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1023\/A:1007514623589.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/article\/10.1023\/A:1007514623589\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1023\/A:1007514623589.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:31:53Z","timestamp":1752147113000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/link.springer.com\/10.1023\/A:1007514623589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,11]]},"references-count":41,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[1998,11]]}},"alternative-id":["186718"],"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1023\/a:1007514623589","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[1998,11]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}