Linear-quadratic zero-sum mean-field type games: optimality conditions and policy optimization
From MaRDI portal
Publication:2068797
Abstract: In this paper, zero-sum mean-field type games (ZSMFTG) with linear dynamics and quadratic cost are studied under infinite-horizon discounted utility function. ZSMFTG are a class of games in which two decision makers whose utilities sum to zero, compete to influence a large population of indistinguishable agents. In particular, the case in which the transition and utility functions depend on the state, the action of the controllers, and the mean of the state and the actions, is investigated. The optimality conditions of the game are analysed for both open-loop and closed-loop controls, and explicit expressions for the Nash equilibrium strategies are derived. Moreover, two policy optimization methods that rely on policy gradient are proposed for both model-based and sample-based frameworks. In the model-based case, the gradients are computed exactly using the model, whereas they are estimated using Monte-Carlo simulations in the sample-based case. Numerical experiments are conducted to show the convergence of the utility function as well as the two players' controls.
Recommendations
- Linear-quadratic mean field stochastic zero-sum differential games
- A mean field approach for discounted zero-sum games in a class of systems of interacting objects
- A closed-loop saddle point for zero-sum linear-quadratic stochastic differential games with mean-field type
- Optimal control and zero-sum stochastic differential game problems of mean-field type
- Linear-quadratic mean-field-type games: a direct method
Cites work
- \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.
- A fully discrete semi-Lagrangian scheme for a first order mean field game problem
- An extended mean field game for storage in smart grids
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- Discrete-time linear-quadratic mean-field-type repeated games: perfect, incomplete, and imperfect information
- Existence and comparison theorems for algebraic Riccati equations for continuous- and discrete-time systems
- Game theory with engineering applications
- scientific article; zbMATH DE number 3388902 (Why is no real title available?)
- Inverses of 2 2 block matrices
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Linear quadratic stochastic two-person zero-sum differential games in an infinite horizon
- Mean field control and mean field game models with several populations
- Mean field game of controls and an application to trade crowding
- Mean field games
- Mean field games and applications: numerical aspects
- Mean field games and mean field type control theory
- Mean field games and systemic risk
- Mean Field Games for Modeling Crowd Motion
- 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
- Model-free Q-learning designs for linear discrete-time zero-sum games with application to H^ control
- 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
- Optimal control and zero-sum stochastic differential game problems of mean-field type
- Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
- Proximal methods for stationary mean field games with local couplings
- Representation and control of infinite dimensional systems
- Saddle-point dynamics: conditions for asymptotic stability of saddle points
- Value iteration algorithm for mean-field games
- Zero-sum stochastic differential games of generalized McKean-Vlasov type
Cited in
(4)- Linear quadratic mean field games: decentralized \(O(1/N)\)-Nash equilibria
- \(\epsilon\)-Nash mean-field games for general linear-quadratic systems with applications
- scientific article; zbMATH DE number 7042541 (Why is no real title available?)
- A single player and a mass of agents: A pursuit evasion-like game
This page was built for publication: Linear-quadratic zero-sum mean-field type games: optimality conditions and policy optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2068797)
