×

Learning and self-confirming long-run biases. (English) Zbl 1422.91181

Summary: We consider an ambiguity averse, sophisticated decision maker facing a recurrent decision problem where information is generated endogenously. In this context, we study self-confirming actions as the outcome of a process of active experimentation. We provide inter alia a learning foundation for self-confirming equilibrium with model uncertainty [P. Battigalli et al., “Self-confirming equilibrium and model uncertainty”, Am. Econ. Rev. 105, No. 2, 646–677 (2015; doi:10.1257/aer.20130930)], and we analyze the impact of changes in ambiguity attitudes on convergence to self-confirming equilibria. We identify conditions under which the set of self-confirming equilibrium actions is invariant to changes in ambiguity attitudes, and yet ambiguity aversion may affect the dynamics. Indeed, we argue that ambiguity aversion tends to stifle experimentation, increasing the likelihood that the decision maker gets stuck into suboptimal “certainty traps”.

MSC:

91B06 Decision theory
91A26 Rationality and learning in game theory
93E20 Optimal stochastic control
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Anderson, C., Ambiguity aversion in multi-armed bandit problems, Theory Decis., 72, 15-33 (2012) · Zbl 1274.91110
[2] Arrow, K. J., Essays in the Theory of Risk-Bearing (1971), Markham · Zbl 0215.58602
[3] Arrow, K. J.; Green, J. R., Notes on Expectations Equilibria in Bayesian Settings (1973), Institute for Mathematical Studies in the Social Sciences, Working Paper 33
[6] Billingsley, P., Probability and Measure (2012), John Wiley & Sons, Ltd · Zbl 1236.60001
[8] Cerreia-Vioglio, S.; Maccheroni, F.; Marinacci, M.; Montrucchio, L., Ambiguity and robust statistics, J. Econ. Theory, 148, 974-1049 (2013) · Zbl 1285.91030
[9] Cerreia-Vioglio, S.; Maccheroni, F.; Marinacci, M.; Montrucchio, L., Classical subjective expected utility, Proc. Natl. Acad. Sci. USA, 110, 6754-6759 (2013) · Zbl 1292.91066
[10] Doob, J. L., Application of the theory of martingales, Colloq. Int. Cent. Natl. Rech. Sci., 23-27 (1949) · Zbl 0041.45101
[11] Dynkin, E., Controlled random sequences, Theory Probab. Appl., 10, 1-14 (1965) · Zbl 0137.35801
[12] Easley, D.; Kiefer, N. M., Controlling a stochastic process with unknown parameters, Econometrica, 5, 1045-1064 (1988) · Zbl 0658.93077
[13] Epstein, L. G.; Schneider, M., Learning under ambiguity, Rev. Econ. Stud., 74, 1275-1303 (2007) · Zbl 1206.91020
[14] Esponda, I.; Pouzo, D., Berk-Nash equilibrium: a framework for modeling agents with misspecified models, Econometrica, 84, 1093-1130 (2016) · Zbl 1419.91129
[15] Folland, G., Real Analysis: Modern Techniques and Their Applications (2013), John Wiley & Sons, Ltd
[16] Fudenberg, D.; He, S., Learning and type compatibility in signalling games, Econometrica, 86, 1215-1255 (2018) · Zbl 1396.91039
[17] Fudenberg, D.; Kreps, D. M., Learning in extensive-form games, I: self-confirming equilibria, Games Econ. Behav., 8, 20-55 (1995) · Zbl 0827.90144
[18] Fudenberg, D.; Levine, D. K., Steady state learning and Nash equilibrium, Econometrica, 61, 547-573 (1993) · Zbl 0792.90096
[19] Fudenberg, D.; Levine, D. K., The Theory of Learning in Games (1998), MIT Press: MIT Press Cambridge, MA · Zbl 0939.91004
[20] Fudenberg, D.; Tirole, J., Game Theory (1991), MIT Press: MIT Press Cambridge, MA · Zbl 1339.91001
[21] Gilboa, I.; Schmeidler, D., Maxmin expected utility with a non-unique prior, J. Math. Econ., 18, 141-153 (1989) · Zbl 0675.90012
[22] Gittins, J. C., Multi-Armed Bandit Allocation Indices, Wiley-Interscience Series in Systems and Optimization (1989), John Wiley & Sons, Ltd.: John Wiley & Sons, Ltd. Chichester · Zbl 0699.90068
[23] Hanany, E.; Klibanoff, P., Updating ambiguity averse preferences, B.E. J. Theor. Econ., 9 (2009) · Zbl 1192.91078
[24] Hanany, E.; Klibanoff, P.; Mukerji, S., Incomplete information games with ambiguity averse players, Am. Econ. J. Microecon (2019), Forthcoming
[26] Hinderer, K., Foundations of Non-stationary Dynamic Programming with Discrete Time Parameter (1970), Springer Science & Business Media · Zbl 0202.18401
[27] Jewitt, I. E.; Mukerji, S., Ordering ambiguous acts, J. Econ. Theory, 171, 213-267 (2017) · Zbl 1400.91179
[28] Kalai, E.; Lehrer, E., Rational learning leads to Nash equilibrium, Econometrica, 1, 1019-1045 (1993) · Zbl 0793.90106
[29] Kalai, E.; Lehrer, E., Subjective games and equilibria, Games Econ. Behav., 8, 123-163 (1995) · Zbl 0833.90143
[30] Klibanoff, P.; Marinacci, M.; Mukerji, S., A smooth model of decision making under ambiguity, Econometrica, 73, 1849-1892 (2005) · Zbl 1151.91372
[31] Li, J., The k-armed bandit problem with multiple-priors, J. Math. Econ., 80, 22-38 (2019) · Zbl 1419.91225
[33] Marinacci, M., Learning from ambiguous urns, Stat. Pap., 43, 143-151 (2002) · Zbl 1059.62510
[34] Marinacci, M., Model uncertainty, J. Eur. Econ. Assoc., 13, 998-1076 (2015)
[35] Rothschild, M., A two-armed bandit theory of market pricing, J. Econ. Theory, 9, 185-202 (1974)
[36] Sion, M., On general minimax theorems, Pac. J. Math., 171, 176 (1958) · Zbl 0163.38203
[37] Williams, D., Probability with Martingales (1991), Cambridge University Press: Cambridge University Press Cambridge · Zbl 0722.60001
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.