A Taxonomy of Learning Dynamics in 2 × 2 Games

Do boundedly rational players learn to choose equilibrium strategies as they play a game repeatedly? A large literature in behavioral game theory has proposed and experimentally tested various learning algorithms, but a comparative analysis of their equilibrium convergence properties is lacking. In this paper we analyze Experience-Weighted Attraction (EWA), which generalizes fictitious play, best reply dynamics, reinforcement learning and also replicator dynamics. We provide a comprehensive analytical characterization of the asymptotic behavior of EWA learning in 2x2 games. We recover some well-known results in the limiting cases in which EWA reduces to the learning rules that it generalizes, but also obtain new results for other parameterizations. For example, we show that in coordination games EWA may only converge to the Pareto-efficient equilibrium, never reaching the Pareto-inefficient one; that in Prisoner Dilemma games it may converge to fixed points of mutual cooperation; and that in Matching Pennies games it may fail to converge to any fixed point, following instead limit cycles or chaos