Semi-Decentralized Coordinated Online Learning for Continuous Games with Coupled Constraints via Augmented Lagrangian

TL;DR

This paper introduces a semi-decentralized online learning algorithm for continuous games with coupled constraints, combining mirror ascent and augmented Lagrangian methods to efficiently reach Nash equilibria.

Contribution

It proposes a novel semi-decentralized algorithm that enables players to learn Nash equilibria in coupled constraint games without full population knowledge or centralized control.

Findings

Algorithm converges to a generalized Nash equilibrium under certain conditions.

Players only need local information and broadcasted prices, not full population data.

The method integrates mirror ascent with augmented Lagrangian for online learning.

Abstract

We consider a class of concave continuous games in which the corresponding admissible strategy profile of each player underlies affine coupling constraints. We propose a novel algorithm that leads the relevant population dynamic toward Nash equilibrium. This algorithm is based on a mirror ascent algorithm, which suits with the framework of no-regret online learning, and on the augmented Lagrangian method. The decentralization aspect of the algorithm corresponds to the aspects that the iterate of each player requires the local information about how she contributes to the coupling constraints and the price vector broadcasted by a central coordinator. So each player needs not know about the population action. Moreover, no specific control by the central primary coordinator is required. We give a condition on the step sizes and the degree of the augmentation of the Lagrangian, such that the proposed algorithm converges to a generalized Nash equilibrium.