Heterogeneous beliefs and local information in stochastic fictitious play

Stochastic fictitious play (SFP) assumes that agents do not try to influence the future play of their current opponents, an assumption that is justified by appeal to a setting with a large population of players who are randomly matched to play the game. However, the dynamics of SFP have only been analyzed in models where all agents in a player role have the same beliefs. We analyze the dynamics of SFP in settings where there is a population of agents who observe only outcomes in their own matches and thus have heterogeneous beliefs. We provide conditions that ensure that the system converges to a state with homogeneous beliefs, and that its asymptotic behavior is the same as with a single representative agent in each player role.

[1]  A. W. Tucker,et al.  Advances in game theory , 1964 .

[2]  Glenn Ellison.  Learning, Local Interaction, and Coordination , 1993 .

[3]  Odile Brandière,et al.  Some Pathological Traps for Stochastic Approximation , 1998 .

[4]  I. Bateman,et al.  A Test of the Theory of Reference-Dependent Preferences , 1997 .

[5]  Martin Posch,et al.  Attainability of boundary points under reinforcement learning , 2005, Games Econ. Behav..

[6]  T. Koopmans,et al.  Activity Analysis of Production and Allocation. , 1952 .

[7]  William H. Sandholm,et al.  ON THE GLOBAL CONVERGENCE OF STOCHASTIC FICTITIOUS PLAY , 2002 .

[8]  Josef Hofbauer,et al.  Learning in perturbed asymmetric games , 2005, Games Econ. Behav..

[9]  William H. Sandholm,et al.  Evolution in Bayesian games II: Stability of purified equilibria , 2007, J. Econ. Theory.

[10]  M. Hirsch,et al.  Mixed Equilibria and Dynamical Systems Arising from Fictitious Play in Perturbed Games , 1999 .

[11]  L. Shapley.  SOME TOPICS IN TWO-PERSON GAMES , 1963 .

[12]  P. DeMarzo,et al.  Persuasion Bias, Social Influence, and Uni-Dimensional Opinions , 2001 .

[13]  E. Hilgard,et al.  Theories of Learning , 1981 .

[14]  Andreu Mas-Colell,et al.  A General Class of Adaptive Strategies , 1999, J. Econ. Theory.

[15]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[16]  Nathaniel T. Wilcox,et al.  Theories of Learning in Games and Heterogeneity Bias , 2006 .

[17]  O. H. Brownlee,et al.  ACTIVITY ANALYSIS OF PRODUCTION AND ALLOCATION , 1952 .

[18]  Dean Phillips Foster,et al.  Regret Testing: Learning to Play Nash Equilibrium Without Knowing You Have an Opponent , 2006 .

[19]  Drew Fudenberg,et al.  Random Matching in Adaptive Dynamics , 2006, Games Econ. Behav..

[20]  H. Young,et al.  Learning dynamics in games with stochastic perturbations , 1995 .

[21]  Josef Hofbauer,et al.  Stochastic Approximations and Differential Inclusions , 2005, SIAM J. Control. Optim..

[22]  R. Pemantle,et al.  Nonconvergence to Unstable Points in Urn Models and Stochastic Approximations , 1990 .

[23]  Larry Samuelson,et al.  Common Learning , 2006 .

[24]  S. Vajda.  Some topics in two-person games , 1971 .

[25]  S. Hart,et al.  A simple adaptive procedure leading to correlated equilibrium , 2000 .

[26]  E. Hopkins.  A Note on Best Response Dynamics , 1999 .

[27]  Glenn Ellison,et al.  Learning from Personal Experience: One Rational Guy and the Justification of Myopia , 1997 .

[28]  D. Fudenberg,et al.  Measuring Players' Losses in Experimental Games , 1997 .

[29]  N. Pimlott.  Learning from the neighbours. , 2012, Canadian family physician Medecin de famille canadien.

[30]  William H. Sandholm,et al.  Evolution in Bayesian games I: Theory , 2005, Games Econ. Behav..

[31]  Sanjeev Goyal,et al.  Learning from Neighbors , 1995 .

[32]  Learning Processes, Mixed Equilibria and Dynamical Systems , 1999 .

[33]  C. Conley.  Isolated Invariant Sets and the Morse Index , 1978 .

[34]  Drew Fudenberg,et al.  Learning Purified Mixed Equilibria , 2000, J. Econ. Theory.

[35]  M. Benaïm,et al.  Deterministic Approximation of Stochastic Evolution in Games , 2003 .

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

[37]  Glenn Ellison,et al.  Rules of Thumb for Social Learning , 1993, Journal of Political Economy.

[38]  Larry Samuelson,et al.  Common learning with intertemporal dependence , 2011, Int. J. Game Theory.

[39]  B. Golub,et al.  Naive Learning in Social Networks: Convergence, Influence and Wisdom of Crowds , 2007 .

[40]  E. Hopkins.  Two Competing Models of How People Learn in Games (first version) , 1999 .

[41]  Odile Brandi Ere.  SOME PATHOLOGICAL TRAPS FOR STOCHASTIC APPROXIMATION , 1998 .

[42]  S. Hart,et al.  A general class of adaptative strategies , 1999 .

[43]  M. Benaïm.  Dynamics of stochastic approximation algorithms , 1999 .

[44]  J. Harsanyi.  Games with randomly disturbed payoffs: A new rationale for mixed-strategy equilibrium points , 1973 .

[45]  D. Freedman,et al.  On the uniform consistency of Bayes estimates for multinomial probabilities , 1990 .

[46]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[47]  O. Brandière,et al.  Les algorithmes stochastiques contournent-ils les pièges? , 1995 .

[48]  Dean P. Foster,et al.  Regret Testing: A Simple Payo-Based Procedure for Learning Nash Equilibrium , 2005 .

[49]  Josef Hofbauer,et al.  Learning in games with unstable equilibria , 2005, J. Econ. Theory.

[50]  H. Young,et al.  The Evolution of Conventions , 1993 .

[51]  Josef Hofbauer,et al.  Evolution in games with randomly disturbed payoffs , 2007, J. Econ. Theory.

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

[53]  J. Jordan.  Three Problems in Learning Mixed-Strategy Nash Equilibria , 1993 .

[54]  D. Fudenberg,et al.  Consistency and Cautious Fictitious Play , 1995 .

[55]  Drew Fudenberg,et al.  Learning Purified Equilibria , 2000 .

[56]  E. Hopkins.  Learning, Matching and Aggregation , 1995 .

[57]  S. Goyal,et al.  Learning from neighbours , 1998 .

[58]  Matthew O. Jackson,et al.  Näıve Learning in Social Networks : Convergence , Influence , and the Wisdom of Crowds ∗ , 2007 .

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