Generalized conditional gradient and learning in potential mean field games
From MaRDI portal
Publication:6072098
exploitabilityfictitious playgeneralized conditional gradientlearningmean field gamesmean field optimal control
Hamilton-Jacobi equations (35F21) PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) Optimality conditions for problems involving partial differential equations (49K20) Methods of reduced gradient type (90C52) Mean field games (aspects of game theory) (91A16) Rationality and learning in game theory (91A26) Decision theory (91B06)
Abstract: We investigate the resolution of second-order, potential, and monotone mean field games with the generalized conditional gradient algorithm, an extension of the Frank-Wolfe algorithm. We show that the method is equivalent to the fictitious play method. We establish rates of convergence for the optimality gap, the exploitability, and the distances of the variables to the unique solution of the mean field game, for various choices of stepsizes. In particular, we show that linear convergence can be achieved when the stepsizes are computed by linesearch.
Recommendations
- Learning in mean field games: The fictitious play
- Learning Optimal Policies in Potential Mean Field Games: Smoothed Policy Iteration Algorithms
- A General Framework for Learning Mean-Field Games
- Finite mean field games: fictitious play and convergence to a first order continuous mean field game
- Continuous time learning algorithms in optimization and game theory
Cites work
- A Cucker-Smale inspired deterministic mean field game with velocity interactions
- A generalized conditional gradient method and its connection to an iterative shrinkage method
- A policy iteration method for mean field games
- An entropy minimization approach to second-order variational mean-field games
- Augmented Lagrangian methods for transport optimization, mean field games and degenerate elliptic equations
- Controlled Markov processes and viscosity solutions
- Discrete potential mean field games: duality and numerical resolution
- Finite mean field games: fictitious play and convergence to a first order continuous mean field game
- scientific article; zbMATH DE number 3322278 (Why is no real title available?)
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Learning in mean field games: The fictitious play
- Mean field game of controls and an application to trade crowding
- Mean field games
- Mean field games and applications: numerical aspects
- Numerical Optimization
- On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings
- Proximal methods for stationary mean field games with local couplings
- Rates of convergence for the policy iteration method for mean field games systems
- Schauder estimates for a class of potential mean field games of controls
- Second order mean field games with degenerate diffusion and local coupling
- Stable solutions in potential mean field game systems
- Variational mean field games for market competition
- Weak solutions for potential mean field games of controls
Cited in
(10)- Learning in mean field games: The fictitious play
- A fast proximal gradient method and convergence analysis for dynamic mean field planning
- Learning Optimal Policies in Potential Mean Field Games: Smoothed Policy Iteration Algorithms
- Game on Random Environment, Mean-Field Langevin System, and Neural Networks
- Forward-backward algorithm for functions with locally Lipschitz gradient: applications to mean field games
- A mesh-independent method for second-order potential mean field games
- A nonsmooth Frank-Wolfe algorithm through a dual cutting-plane approach
- Learning equilibria in Cournot mean field games of controls
- Mean field optimization problems: stability results and Lagrangian discretization
- On the generalized conditional gradient method for mean field games with local coupling terms
This page was built for publication: Generalized conditional gradient and learning in potential mean field games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6072098)
