Basins of attraction and equilibrium selection under different learning rules

A deterministic learning model applied to a game with multiple equilibria produces distinct basins of attraction for those equilibria. In symmetric two-by-two games, basins of attraction are invariant to a wide range of learning rules including best response dynamics, replicator dynamics, and fictitious play. In this paper, we construct a class of three-by-three symmetric games for which the overlap in the basins of attraction under best response learning and replicator dynamics is arbitrarily small. We then derive necessary and sufficient conditions on payoffs for these two learning rules to create basins of attraction with vanishing overlap. The necessary condition requires that with probability one the initial best response is not an equilibrium to the game. The existence of parasitic or misleading actions allows subtle differences in the learning rules to accumulate.

[1]  A. Roth,et al.  Predicting How People Play Games: Reinforcement Learning in Experimental Games with Unique, Mixed Strategy Equilibria , 1998 .

[2]  J. Hofbauer,et al.  Evolutionary game dynamics , 2011 .

[3]  William H. Sandholm,et al.  Pairwise Comparison Dynamics and Evolutionary Foundations for Nash Equilibrium , 2009, Games.

[4]  Timothy C. Salmon An Evaluation of Econometric Models of Adaptive Learning , 2001 .

[5]  F. Kojima Stability and instability of the unbeatable strategy in dynamic processes , 2006 .

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

[7]  L. Samuelson Evolutionary Games and Equilibrium Selection , 1997 .

[8]  K Sigmund,et al.  A note on evolutionary stable strategies and game dynamics. , 1979, Journal of theoretical biology.

[9]  John Nachbar “Evolutionary” selection dynamics in games: Convergence and limit properties , 1990 .

[10]  R. Rob,et al.  Learning, Mutation, and Long Run Equilibria in Games , 1993 .

[11]  Bernard Walliser,et al.  A spectrum of equilibration processes in game theory , 1998 .

[12]  Colin Camerer,et al.  Experience‐weighted Attraction Learning in Normal Form Games , 1999 .

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

[14]  James Baldwin,et al.  Complexity and the limits to learning , 2007 .

[15]  R. Cressman Evolutionary Dynamics and Extensive Form Games , 2003 .

[16]  Karl H. Schlag,et al.  Evolutionarily stable sets , 2000, Int. J. Game Theory.

[17]  Nick Feltovich,et al.  Reinforcement-based vs. Belief-based Learning Models in Experimental Asymmetric-information Games , 2000 .

[18]  P. Taylor,et al.  Evolutionarily Stable Strategies and Game Dynamics , 1978 .

[19]  I. Gilboa,et al.  Social Stability and Equilibrium , 1991 .

[20]  J. Neumann,et al.  SOLUTIONS OF GAMES BY DIFFERENTIAL EQUATIONS , 1950 .

[21]  John C. Harsanyi,et al.  Общая теория выбора равновесия в играх / A General Theory of Equilibrium Selection in Games , 1989 .

[22]  Karl Sigmund,et al.  The dynamics of public goods , 2004 .

[23]  K. Schlag Why Imitate, and If So, How?, : A Boundedly Rational Approach to Multi-armed Bandits , 1998 .

[24]  Jeroen M. Swinkels Adjustment Dynamics and Rational Play in Games , 1993 .

[25]  Robert Wilson,et al.  Refinements of Nash Equilibrium , 2005 .

[26]  Drew Fudenberg,et al.  Learning in Games , 1998 .

[27]  L. Samuelson,et al.  Evolutionary Drift and Equilibrium Selection , 2010 .

[28]  Equilibrium selection in coordination games: Why do dominated strategies matter? , 2004 .

[29]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[30]  J. Hofbauer From Nash and Brown to Maynard Smith: Equilibria, Dynamics and ESS , 2001 .

[31]  Scott E. Page,et al.  Individual and cultural learning in stag hunt games with multiple actions , 2010 .

[32]  Glenn Ellison Basins of Attraction, Long-Run Stochastic Stability, and the Speed of Step-by-Step Evolution , 2000 .

[33]  Josef Hofbauer,et al.  Evolutionary Games and Population Dynamics , 1998 .

[34]  S. Page,et al.  A characterization of equilibria in the Groves–Ledyard mechanism , 2010 .

[35]  Reinhard Selten,et al.  The work of John Nash in game theory , 1995 .

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

[37]  D. Stahl,et al.  EMPIRICAL TESTS OF EQUILIBRIUM SELECTION BASED ON PLAYER HETEROGENEITY , 1999 .

[38]  Brian Skyrms,et al.  The Dynamics Of Rational Deliberation , 1990 .

[39]  Dale O. Stahl,et al.  Robust Initial Conditions for Learning Dynamics , 2000 .

[40]  Colin Camerer Behavioral Game Theory: Experiments in Strategic Interaction , 2003 .

[41]  J. M. Smith The theory of games and the evolution of animal conflicts. , 1974, Journal of theoretical biology.

[42]  H. Peyton Young,et al.  Stochastic Evolutionary Game Dynamics , 1990 .