Active learning with a misspecified prior

We study learning and information acquisition by a Bayesian agent whose prior belief is misspecified in the sense that it assigns probability zero to the true state of the world. At each instant, the agent takes an action and observes the corresponding payoff, which is the sum of a fixed but unknown function of the action and an additive error term. We provide a complete characterization of asymptotic actions and beliefs when the agent's subjective state space is a doubleton. A simple example with three actions shows that in a misspecified environment a myopic agent's beliefs converge while a sufficiently patient agent's beliefs do not. This illustrates a novel interaction between misspecification and the agent's subjective discount rate.

[1]  M. Aschwanden.  Statistics of Random Processes , 2021, Biomedical Measurement Systems and Data Science.

[2]  T. Sargent.  The Conquest of American Inflation , 1999 .

[3]  M. A. Girshick,et al.  Bayes and minimax solutions of sequential decision problems , 1949 .

[4]  Steven A. Orszag,et al.  CBMS-NSF REGIONAL CONFERENCE SERIES IN APPLIED MATHEMATICS , 1978 .

[5]  A. McLennan.  Price dispersion and incomplete learning in the long run , 1984 .

[6]  Philippe Jehiel,et al.  Revisiting games of incomplete information with analogy-based expectations , 2008, Games Econ. Behav..

[7]  Drew Fudenberg,et al.  Learning in extensive-form games I. Self-confirming equilibria , 1995 .

[8]  Xiongzhi Chen.  Brownian Motion and Stochastic Calculus , 2008 .

[9]  Philippe Jehiel,et al.  Analogy-based expectation equilibrium , 2004, J. Econ. Theory.

[10]  Kenneth Kasa,et al.  Learning and Model Validation , 2007 .

[11]  Drew Fudenberg,et al.  Stochastic Choice and Optimal Sequential Sampling , 2015, 1505.03342.

[12]  Martin Szydlowski,et al.  On the smoothness of value functions and the existence of optimal strategies in diffusion models , 2015, J. Econ. Theory.

[13]  D. Fudenberg,et al.  Steady state learning and Nash equilibrium , 1993 .

[14]  B. Jullien,et al.  OPTIMAL LEARNING BY EXPERIMENTATION , 1991 .

[15]  Ignacio Esponda.  Behavioral Equilibrium in Economies with Adverse Selection , 2008 .

[16]  Yaw Nyarko,et al.  Learning In Mis-Specified Models And The Possibility Of Cycles , 1991 .

[17]  Ioannis Karatzas,et al.  Brownian Motion and Stochastic Calculus , 1987 .

[18]  Bruno H. Strulovici,et al.  On the Smoothness of Value Functions and the Existence of Optimal Strategies , 2012 .

[19]  H. White,et al.  A Unified Theory of Estimation and Inference for Nonlinear Dynamic Models , 1988 .

[20]  R. Khan,et al.  Sequential Tests of Statistical Hypotheses. , 1972 .

[21]  David M. Kreps,et al.  Learning Mixed Equilibria , 1993 .

[22]  Ignacio Esponda,et al.  Berk-Nash Equilibrium: A Framework for Modeling Agents with Misspecified Models , 2014, 1411.1152.

[23]  D. Fudenberg,et al.  Self-confirming equilibrium , 1993 .

[24]  Eld,et al.  Cursed Equilibrium , 2000 .

[25]  Philipp Strack,et al.  Unrealistic Expectations and Misguided Learning , 2017 .

[26]  N. Kiefer,et al.  Controlling a Stochastic Process with Unknown Parameters , 1988 .

[27]  D. Freedman,et al.  Invariant Probabilities for Certain Markov Processes , 1966 .

[28]  C. Shalizi.  Dynamics of Bayesian Updating with Dependent Data and Misspecified Models , 2009, 0901.1342.

[29]  P. Whittle.  Multi‐Armed Bandits and the Gittins Index , 1980 .

[30]  R. Berk,et al.  Limiting Behavior of Posterior Distributions when the Model is Incorrect , 1966 .

[31]  Lones Smith,et al.  The Optimal Level of Experimentation , 2000 .

[32]  J. Gittins.  Bandit processes and dynamic allocation indices , 1979 .

[33]  N. Kiefer,et al.  Optimal Control of an Unknown Linear Process with Learning , 1989 .

[34]  Ignacio Esponda,et al.  Equilibrium in Misspecified Markov Decision Processes , 2015, Theoretical Economics.

[35]  H. Chernoff.  Sequential Analysis and Optimal Design , 1987 .

[36]  Kenneth J. Arrow,et al.  Notes on Expectations Equilibria in Bayesian Settings Institute for Mathematical Studies in the Social Sciences , 1973 .

[37]  D. Freedman,et al.  On the consistency of Bayes estimates , 1986 .