We establish global convergence results for stochastic fictitious play for four classes of games: games with an interior ESS, zero sum games, potential games, and supermodular games. We do so by appealing to techniques from stochastic approximation theory, which relate the limit behavior of a stochastic process to the limit behavior of a differential equation defined by the expected motion of the process. The key result in our analysis of supermodular games is that the relevant differential equation defines a strongly monotone dynamical system. Our analyses of the other cases combine Lyapunov function arguments with a discrete choice theory result: that the choice probabilities generated by any additive random utility model can be derived from a deterministic model based on payoff perturbations that depend nonlinearly on the vector of choice probabilities.
MLA
Hofbauer, Josef, and William H. Sandholm. “On the Global Convergence of Stochastic Fictitious Play.” Econometrica, vol. 70, .no 6, Econometric Society, 2002, pp. 2265-2294, https://doi.org/10.1111/j.1468-0262.2002.00440.x
Chicago
Hofbauer, Josef, and William H. Sandholm. “On the Global Convergence of Stochastic Fictitious Play.” Econometrica, 70, .no 6, (Econometric Society: 2002), 2265-2294. https://doi.org/10.1111/j.1468-0262.2002.00440.x
APA
Hofbauer, J., & Sandholm, W. H. (2002). On the Global Convergence of Stochastic Fictitious Play. Econometrica, 70(6), 2265-2294. https://doi.org/10.1111/j.1468-0262.2002.00440.x
The Executive Committee of the Econometric Society has approved an increase in the submission fees for papers in Econometrica. Starting January 1, 2025, the fee for new submissions to Econometrica will be US$125 for regular members and US$50 for student members.
By clicking the "Accept" button or continuing to browse our site, you agree to first-party and session-only cookies being stored on your device. Cookies are used to optimize your experience and anonymously analyze website performance and traffic.