Data-Driven Mean Field Equilibrium Computation in Large-Population LQG Games
This paper presents a novel data-driven approach for approximating the $\varepsilon$-Nash equilibrium in continuous-time linear quadratic Gaussian (LQG) games, where multiple agents interact with each other through their dynamics and infinite horizon discounted costs. The core of our method involves solving two algebraic Riccati equations (AREs) and an ordinary differential equation (ODE) using state and input samples collected from agents, eliminating the need for a priori knowledge of their dynamical models. The standard ARE is addressed through an integral reinforcement learning (IRL) technique, while the nonsymmetric ARE and the ODE are resolved by identifying the drift coefficients of the agents' dynamics under general conditions. Moreover, by imposing specific conditions on models, we extend the IRL-based approach to approximately solve the nonsymmetric ARE. Numerical examples are given to demonstrate the effectiveness of the proposed algorithms.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning in Discounted-cost and Average-cost Mean-field Games
We consider learning approximate Nash equilibria for discrete-time mean-field games with nonlinear stochastic state dynamics subject to both average and discounted costs. To this end, we introduce a mean-field equilibriu…
Q-LearningA mean field game approach to equilibrium consumption under external habit formation
This paper studies the equilibrium consumption under external habit formation in a large population of agents. We first formulate problems under two types of conventional habit formation preferences, namely linear and mu…
Relative Arbitrage Opportunities in an Extended Mean Field System
This paper studies relative arbitrage opportunities in a market with infinitely many interacting investors. We establish a conditional McKean-Vlasov system to study the market dynamics coupled with investors. We then pro…
Nonequilibrium thermodynamics of input-driven networks
Neural dynamics of energy-based models are governed by energy minimization and the patterns stored in the network are retrieved when the system reaches equilibrium. However, when the system is driven by time-varying exte…
Machine learning nonequilibrium phase transitions in charge-density wave insulators
Nonequilibrium electronic forces play a central role in voltage-driven phase transitions but are notoriously expensive to evaluate in dynamical simulations. Here we develop a machine learning framework for adiabatic latt…
Computational Efficiency