Special Session 145: Dynamic Models under Uncertainty in Economics and Finance

Learning Algorithm for Mean-Field Coarse Correlated Equilibrium: A Linear Programming Approach
Ioannis Tzouanas
Bielefeld University
Germany
Co-Author(s):    Luciano Campi, Federico Cannerozzi
Abstract:
We investigate the approximation of Coarse Correlated Equilibrium (CCE) within the framework of continuous-time mean-field games. In this setting, a regulator (or a correlation device) recommends strategies that agents have no unilateral incentive to deviate from. We begin by introducing the concept of optimal CCE and reformulating the problem using a linear programming approach to demonstrate existence under weak assumptions. Then, we focus on the approximation of these equilibria, we propose a novel no-regret primal-dual learning algorithm and prove its convergence. Finally, we provide numerical examples to illustrate our results.