A mean-field stochastic control problem with partial observations
From MaRDI portal
conditional mean-field SDEsmean-field backward SDEsnon-Markovian stochastic control systemnonlinear filteringstochastic maximum principle
Applications of operator theory in systems, signals, circuits, and control theory (47N70) Optimality conditions for minimax problems (49K35) Optimality conditions for problems involving randomness (49K45) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of stochastic analysis (to PDEs, etc.) (60H30) Filtering in stochastic control theory (93E11) Optimal stochastic control (93E20)
Abstract: In this paper we are interested in a new type of {it mean-field}, non-Markovian stochastic control problems with partial observations. More precisely, we assume that the coefficients of the controlled dynamics depend not only on the paths of the state, but also on the conditional law of the state, given the observation to date. Our problem is strongly motivated by the recent study of the mean field games and the related McKean-Vlasov stochastic control problem, but with added aspects of path-dependence and partial observation. We shall first investigate the well-posedness of the state-observation dynamics, with combined reference probability measure arguments in nonlinear filtering theory and the Schauder fixed point theorem. We then study the stochastic control problem with a partially observable system in which the conditional law appears nonlinearly in both the coefficients of the system and cost function. As a consequence the control problem is intrinsically "time-inconsistent", and we prove that the Pontryagin Stochastic Maximum Principle holds in this case and characterize the adjoint equations, which turn out to be a new form of mean-field type BSDEs.
Recommendations
- Extended mean-field control problem with partial observation
- The maximum principle for partially observed optimal control problems of mean-field FBSDEs
- Mean field approach to stochastic control with partial information
- Stochastic maximum principle for partially observed optimal control problems of general McKean-Vlasov differential equations
- A maximum principle for mean-field stochastic control system with noisy observation
Cited in
(54)- Discrete-time mean field partially observable controlled systems subject to common noise
- Randomized filtering and Bellman equation in Wasserstein space for partial observation control problem
- Partial derivative with respect to the measure and its application to general controlled mean-field systems
- A maximum principle for mean-field stochastic control system with noisy observation
- Least squares estimation for distribution-dependent stochastic differential delay equations
- Approximations of McKean-Vlasov stochastic differential equations with irregular coefficients
- Quasilinear rough partial differential equations with transport noise
- Distribution-dependent SDEs with Hölder continuous drift and -stable noise
- A general stochastic maximum principle for mean-field controls with regime switching
- A necessary condition for mean-field type stochastic differential equations with correlated state and observation noises
- An optimal control problem for linear SDE of mean-field type with terminal constraint and partial information
- Mean-field linear-quadratic stochastic differential games in an infinite horizon
- Mean field approach to stochastic control with partial information
- The solution of a partially observed stochastic optimal control problem in terms of predicted miss
- Kyle-Back equilibrium models and linear conditional mean-field SDEs
- Near optimality of stochastic control for singularly perturbed McKean-Vlasov systems
- Extended mean-field control problem with partial observation
- A stochastic maximum principle for switching diffusions using conditional mean-fields with applications to control problems
- A stochastic maximum principle for general mean-field systems
- scientific article; zbMATH DE number 5227820 (Why is no real title available?)
- Dynamic Programming for Optimal Control of Stochastic McKean--Vlasov Dynamics
- A stochastic maximum principle for partially observed general mean-field control problems with only weak solution
- Discrete-time mean-field stochastic control with partial observations
- Partially observed risk-sensitive stochastic control problems with non-convexity restriction
- A general conditional McKean-Vlasov stochastic differential equation
- Multiple-delay stochastic McKean-Vlasov equations with Hölder diffusion coefficients and their numerical schemes
- McKean-Vlasov stochastic differential equations driven by the time-changed Brownian motion
- Partial information maximum principle for optimal control problem with regime switching in the conditional mean-field model
- Online parameter estimation for the McKean-Vlasov stochastic differential equation
- Convergence rate in \(\mathcal{L}^p\) sense of tamed EM scheme for highly nonlinear neutral multiple-delay stochastic McKean-Vlasov equations
- A unified approach to linear-quadratic-Gaussian mean-field team: homogeneity, heterogeneity and quasi-exchangeability
- Linear-Quadratic Large-Population Problem with Partial Information: Hamiltonian Approach and Riccati Approach
- Markovian-switching systems: backward and forward-backward stochastic differential equations, mean-field interactions, and nonzero-sum differential games
- A branching particle system approximation for solving partially observed stochastic optimal control problems via stochastic maximum principle
- Sign-indefinite static output feedback Nash strategy for mean-field stochastic systems
- Optimal control of LQ problem with anticipative partial observations
- Stochastic recursive optimal control of McKean-Vlasov type: a viscosity solution approach
- Incomplete information mean-field games and related Riccati equations
- Multilevel Monte Carlo EM scheme for MV-SDEs with small noise
- Numerical analysis for mean-field type stochastic differential equations with piecewise continuous arguments
- Strong convergence of Euler scheme for McKean-Vlasov stochastic variational inequalities with locally Hölder continuous diffusion coefficients
- Linear quadratic optimal control problems for conditional mean-field stochastic differential equations under partial information
- Mean-field backward stochastic differential equations with random terminal time
- Maximum principles for conditional mean field type control problems under partial and full observation with applications
- Mean-field stochastic control problems under sublinear expectation
- Mean field type control problems, some Hilbert-space-valued FBSDES, and related equations
- Mean-field partial information non-zero sum stochastic differential games
- Doubly perturbed distribution dependent stochastic differential equation
- Distribution dependent stochastic differential equations driven by fractional Brownian motion and standard Brownian motion
- Superpositions for general conditional Mckean-Vlasov stochastic differential equations
- Global well-posedness of first-order mean field games and master equations with nonlinear dynamics
- Pseudo almost automorphic solutions to delayed McKean-Vlasov integro-differential equations with Lévy noise and its optimal control
- A necessary condition for partially observable mean-field type optimal control system with terminal state constraint
- Viability of McKean-Vlasov stochastic differential equations driven by time-changed Brownian motion
This page was built for publication: A mean-field stochastic control problem with partial observations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1688031)
