A policy iteration method for mean field games
From MaRDI portal
Publication:3383295
DOI10.1051/COCV/2021081zbMath1473.49043arXiv2007.04818OpenAlexW3178011931MaRDI QIDQ3383295
Simone Cacace, Alessandro Goffi, Fabio Camilli
Publication date: 23 September 2021
Published in: ESAIM: Control, Optimisation and Calculus of Variations (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2007.04818
Newton-type methods (49M15) Differential games and control (49N70) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Mean field games (aspects of game theory) (91A16)
Related Items (7)
Rates of convergence for the policy iteration method for mean field games systems ⋮ Convergence of deep fictitious play for stochastic differential games ⋮ Generalized conditional gradient and learning in potential mean field games ⋮ Policy iteration method for time-dependent mean field games systems with non-separable Hamiltonians ⋮ Learning Optimal Policies in Potential Mean Field Games: Smoothed Policy Iteration Algorithms ⋮ Model-free policy iteration approach to NCE-based strategy design for linear quadratic Gaussian games ⋮ On quasi-stationary Mean Field Games of Controls
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On the system of partial differential equations arising in mean field type control
- A semi-Lagrangian scheme for a degenerate second order mean field game system
- Nonlinear elliptic systems and mean-field games
- Mean field games
- On the convergence of policy iteration for controlled diffusions
- Optimal control of diffusion processes with reflection
- Mean field games of timing and models for bank runs
- Stable solutions in potential mean field game systems
- Quelques remarques sur les problèmes elliptiques quasilinéaires du second ordre. (Some remarks on second order quasilinear elliptic problems)
- Long time average of mean field games
- On the problem of maximal \(L^q\)-regularity for viscous Hamilton-Jacobi equations
- Lipschitz regularity for viscous Hamilton-Jacobi equations with \(L^p\) terms
- Mean field games and applications: numerical aspects
- Optimality of integrability estimates for advection-diffusion equations
- A Generalized Newton Method for Homogenization of Hamilton--Jacobi Equations
- Mean Field Games: Convergence of a Finite Difference Method
- Learning in mean field games: The fictitious play
- An Efficient Policy Iteration Algorithm for Dynamic Programming Equations
- Global Properties of Transition Probabilities of Singular Diffusions
- Some Convergence Results for Howard's Algorithm
- On the Convergence of Policy Iteration in Stationary Dynamic Programming
- Proximal Methods for Stationary Mean Field Games with Local Couplings
- On the Existence and Uniqueness of Solutions to Time-Dependent Fractional MFG
- Interpolation Theory
- Convergence Properties of Policy Iteration
- Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions
- Linear-Quadratic $N$-person and Mean-Field Games with Ergodic Cost
- 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: A policy iteration method for mean field games
