A Verification Framework for Fictitious Play Based Learning Algorithms
Michalis Smyrnakis, Hongyang Qu, Sándor M. Veres · 2015
Distributed optimisation techniques have gained increasing attention due to fast development of autonomous robots. Many algorithms have been proposed to make optimisation more efficient. In this paper we propose a framework, which is based on probabilistic verification techniques, in order to compare the performance of various game-theoretic algorithms, in particular, fictitious play and its variants, after a finite number of iterations. To demonstrate the effectiveness of the framework, we apply the framework to a game which is inspired by wireless communication network problems, on five variations of fictitious play algorithms.