Numerical methods for mean field games based on Gaussian processes and Fourier features

DOI10.1016/j.jcp.2022.111188OpenAlexW4200632387WikidataQ114163327 ScholiaQ114163327MaRDI QIDQ2137987

Chenchen Mou, Xianjin Yang, Chao Zhou

Publication date: 11 May 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.05414

zbMATH Keywords

Gaussian processmean field gamesFourier features

Mathematics Subject Classification ID

Game theory (91Axx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Partial differential equations of mathematical physics and other areas of application (35Qxx)

Related Items (3)

Random features for high-dimensional nonlocal mean-field games ⋮ Machine learning architectures for price formation models ⋮ Sparse Gaussian processes for solving nonlinear PDEs

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mean field games. I: The stationary case
• Mean field games. II: Finite horizon and optimal control
• Augmented Lagrangian methods for transport optimization, mean field games and degenerate elliptic equations
• Mean field games
• Two numerical approaches to stationary mean-field games
• First-order, stationary mean-field games with congestion
• On stationary fractional mean field games
• Iterative strategies for solving linearized discrete mean field games systems
• Numerical methods for finite-state mean-field games satisfying a monotonicity condition
• Solving and learning nonlinear PDEs with Gaussian processes
• Kernel flows: from learning kernels from data into the abyss
• Mean field games and applications: numerical aspects
• A mean-field game approach to price formation
• Fourier approximation methods for first-order nonlocal mean-field games
• An invariance principle in large population stochastic dynamic games
• Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
• Mean Field Games: Numerical Methods for the Planning Problem
• Mean Field Games and Applications
• Proximal Methods for Stationary Mean Field Games with Local Couplings
• Consistency of empirical Bayes and kernel flow for hierarchical parameter estimation
• Operator-Adapted Wavelets, Fast Solvers, and Numerical Homogenization
• On the implementation of a primal-dual algorithm for second order time-dependent Mean Field Games with local couplings
• The Hessian Riemannian flow and Newton’s method for effective Hamiltonians and Mather measures
• Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games I: The Ergodic Case
• Computational Methods for First-Order Nonlocal Mean Field Games with Applications
• Mean Field Games for Modeling Crowd Motion
• Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
• Mean Field Games: Numerical Methods

This page was built for publication: Numerical methods for mean field games based on Gaussian processes and Fourier features