Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. II: The finite horizon case
From MaRDI portal
Publication:2108885
machine learningmean field gamesnumerical approximationforward-backward SDEmean field controlMcKean-Vlasov
Artificial neural networks and deep learning (68T07) Neural networks for/in biological studies, artificial life and related topics (92B20) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Vlasov equations (35Q83) PDEs in connection with control and optimization (35Q93) PDEs with randomness, stochastic partial differential equations (35R60) Numerical solutions to stochastic differential and integral equations (65C30) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Stability and convergence of numerical methods for initial value and initial-boundary value problems involving PDEs (65M12) Error bounds for initial value and initial-boundary value problems involving PDEs (65M15) Optimal stochastic control (93E20) Mean field games and control (49N80) Mean field games (aspects of game theory) (91A16) PDEs in connection with mean field game theory (35Q89)
Abstract: We propose two numerical methods for the optimal control of McKean-Vlasov dynamics in finite time horizon. Both methods are based on the introduction of a suitable loss function defined over the parameters of a neural network. This allows the use of machine learning tools, and efficient implementations of stochastic gradient descent in order to perform the optimization. In the first method, the loss function stems directly from the optimal control problem. The second method tackles a generic forward-backward stochastic differential equation system (FBSDE) of McKean-Vlasov type, and relies on suitable reformulation as a mean field control problem. To provide a guarantee on how our numerical schemes approximate the solution of the original mean field control problem, we introduce a new optimization problem, directly amenable to numerical computation, and for which we rigorously provide an error rate. Several numerical examples are provided. Both methods can easily be applied to certain problems with common noise, which is not the case with the existing technology. Furthermore, although the first approach is designed for mean field control problems, the second is more general and can also be applied to the FBSDE arising in the theory of mean field games.
Recommendations
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- CEMRACS 2017: numerical probabilistic approach to MFG
- Numerical resolution of McKean-Vlasov FBSDEs using neural networks
- Numerical methods for mean-field type optimal control problems
- A class of finite-dimensional numerically solvable McKean-Vlasov control problems
Cites work
- scientific article; zbMATH DE number 4211245 (Why is no real title available?)
- $L^2$-Multivariate Approximation Theory
- A class of finite-dimensional numerically solvable McKean-Vlasov control problems
- A fully discrete semi-Lagrangian scheme for a first order mean field game problem
- A probabilistic approach to classical solutions of the master equation for large population equilibria
- A stochastic particle method for the McKean-Vlasov and the Burgers equation
- An ergodic problem for Mean Field Games: qualitative properties and numerical simulations
- CEMRACS 2017: numerical probabilistic approach to MFG
- Contract theory in continuous-time models
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- Convergence of the deep BSDE method for coupled FBSDEs
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Degree of approximation by neural and translation networks with a single hidden layer
- Dynamic programming approach to principal-agent problems
- Dynamic programming for mean-field type control
- Long time average of first order mean field games and weak KAM theory
- Mean Field Games for Modeling Crowd Motion
- Mean field games
- Mean field games and mean field type control theory
- Mean field games and systemic risk
- Mean field games: numerical methods
- Mean field games: numerical methods for the planning problem
- Mean field type control with congestion. II: An augmented Lagrangian method
- Numerical method for FBSDEs of McKean-Vlasov type
- Numerical methods for mean-field type optimal control problems
- On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings
- On the system of partial differential equations arising in mean field type control
- Optimization methods for large-scale machine learning
- Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
- Probabilistic theory of mean field games with applications II. Mean field games with common noise and master equations
- Proximal methods for stationary mean field games with local couplings
- Sensitivity Analysis Using Itô--Malliavin Calculus and Martingales, and Application to Stochastic Optimal Control
- The Master Equation and the Convergence Problem in Mean Field Games
- Two numerical approaches to stationary mean-field games
Cited in
(24)- A class of finite-dimensional numerically solvable McKean-Vlasov control problems
- A level-set approach to the control of state-constrained McKean-Vlasov equations: application to renewable energy storage and portfolio selection
- A Lagrange–Galerkin Scheme for First Order Mean Field Game Systems
- Learning High-Dimensional McKean–Vlasov Forward-Backward Stochastic Differential Equations with General Distribution Dependence
- Numerical resolution of McKean-Vlasov FBSDEs using neural networks
- Learning a functional control for high-frequency finance
- Importance sampling for the empirical measure of weakly interacting diffusions
- Convergence of the Backward Deep BSDE Method with Applications to Optimal Stopping Problems
- Recent developments in machine learning methods for stochastic control and games
- A posteriori estimate for a class of mean-field forward-backward stochastic differential equations
- Deep neural network solution for finite state mean field game with error estimation
- Numerical methods for backward stochastic differential equations: a survey
- Unified reinforcement Q-learning for mean field game and control problems
- Relative wealth concerns with partial information and heterogeneous priors
- Sequential propagation of chaos for mean-field BSDE systems
- Connecting GANs, mean-field games, and optimal transport
- A fast iterative PDE-based algorithm for feedback controls of nonsmooth mean-field control problems
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- Computational mean-field games on manifolds
- Performance of a Markovian neural network versus dynamic programming on a fishing control problem
- Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning
- Nonstandard stochastic control with nonlinear Feynman-Kac costs
- Approximation of optimal feedback controls for stochastic reaction-diffusion equations
- On numerical approximations of fractional and nonlocal mean field games
This page was built for publication: Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. II: The finite horizon case
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2108885)
