Predicting human behavior in unrepeated, simultaneous-move games

It is common to assume that agents will adopt Nash equilibrium strategies; however, experimental studies have demonstrated that Nash equilibrium is often a poor description of human players’ behavior in unrepeated normal-form games. In this paper, we analyze five widely studied models (QRE, Lk, Cognitive Hierarchy, QLk, and Noisy Introspection) that aim to describe actual, rather than idealized, human behavior in such games. We performed what we believe is the most comprehensive meta-analysis of these models, leveraging ten different data sets from the literature recording human play of two-player games. We began by evaluating the models’ generalization or predictive performance, asking how well a model fits unseen test data after having had its parameters calibrated based on separate training data. Surprisingly, we found that what we dub the QLk model of Stahl and Wilson (1994) consistently achieved the best performance. Motivated by this finding, we describe methods for analyzing the posterior distributions over a model’s parameters. We found that QLk’s parameters were being set to values that were not consistent with their intended economic interpretations. We thus explored variations of QLk, ultimately identifying a new model family that has fewer parameters, gives rise to more parsimonious IPreliminary versions of portions of this work appeared in the proceedings of two computer science conferences (Wright and Leyton-Brown, 2010, 2012). ∗Principal corresponding author, Telephone +1 604 827 3924 ∗∗Corresponding author, Telephone +1 604 822 1453 Email addresses: [email protected] (James R. Wright), [email protected] (Kevin Leyton-Brown) Preprint submitted to Elsevier August 22, 2016 ar X iv :1 30 6. 09 18 v3 [ cs .G T ] 1 9 A ug 2 01 6 parameter values, and achieves better predictive performance.