Data-Driven Network LQG Mean Field Games with Heterogeneous Populations via Integral Reinforcement Learning

TL;DR

This paper introduces a data-driven approach using Integral Reinforcement Learning to solve infinite horizon linear quadratic Gaussian Mean Field Games with heterogeneous populations, without requiring knowledge of agent dynamics.

Contribution

It develops a novel data-driven algorithm that leverages trajectory data and Kleinman's iteration to solve network-coupled MFGs with unknown dynamics, ensuring convergence under certain conditions.

Findings

Algorithm successfully learns MFG strategies from data.

Convergence to true strategies is proven under technical conditions.

Applicable to heterogeneous agent populations with network coupling.

Abstract

This paper establishes a data-driven solution for infinite horizon linear quadratic Gaussian Mean Field Games with network-coupled heterogeneous agent populations where the dynamics of the agents are unknown. The solution technique relies on Integral Reinforcement Learning and Kleinman's iteration for solving algebraic Riccati equations (ARE). The resulting algorithm uses trajectory data to generate network-coupled MFG strategies for agents and does not require parameters of agents' dynamics. Under technical conditions on the persistency of excitation and on the existence of unique stabilizing solution to the corresponding AREs, the learned network-coupled MFG strategies are shown to converge to their true values.