Mean Field Games with Partial Observation
From MaRDI portal
PDEs in connection with control and optimization (35Q93) PDEs with randomness, stochastic partial differential equations (35R60) Signal detection and filtering (aspects of stochastic processes) (60G35) Noncooperative games (91A10) Differential games (aspects of game theory) (91A23) Decentralized systems (93A14) Optimal stochastic control (93E20)
Abstract: Subject to reasonable conditions, in large population stochastic dynamics games, where the agents are coupled by the system's mean field (i.e. the state distribution of the generic agent) through their nonlinear dynamics and their nonlinear cost functions, it can be shown that a best response control action for each agent exists which (i) depends only upon the individual agent's state observations and the mean field, and (ii) achieves a -Nash equilibrium for the system. In this work we formulate a class of problems where each agent has only partial observations on its individual state. We employ nonlinear filtering theory and the Separation Principle in order to analyze the game in the asymptotically infinite population limit. The main result is that the -Nash equilibrium property holds where the best response control action of each agent depends upon the conditional density of its own state generated by a nonlinear filter, together with the system's mean field. Finally, comparing this MFG problem with state estimation to that found in the literature with a major agent whose partially observed state process is independent of the control action of any individual agent, it is seen that, in contrast, the partially observed state process of any agent in this work depends upon that agent's control action.
Recommendations
- Mean-payoff games with partial observation
- Mean field game theory with a partially observed major agent
- Mean-payoff games with partial-observation (extended abstract)
- Partially observed discrete-time risk-sensitive mean field games
- Approximate Nash equilibria in partially observed stochastic games with mean-field interactions
- Linear-quadratic-Gaussian mean-field-game with partial observation and common noise
- Mean field games and applications
- Mean Field Games With Parametrized Followers
- Mean-field-type games
- Some remarks on mean field games
Cites work
- \epsilon-Nash Equilibria for Partially Observed LQG Mean Field Games With a Major Player
- -Nash mean field game theory for nonlinear stochastic dynamical systems with major and minor agents
- A probabilistic approach to mean field games with major and minor players
- Certain nonlinear partially observable stochastic optimal control problems with explicit control laws equivalent to LEQG/LQG problems
- Exact finite-dimensional filters for certain diffusions with nonlinear drift
- Fundamentals of stochastic filtering
- scientific article; zbMATH DE number 4211245 (Why is no real title available?)
- scientific article; zbMATH DE number 3718234 (Why is no real title available?)
- scientific article; zbMATH DE number 49106 (Why is no real title available?)
- scientific article; zbMATH DE number 1325009 (Why is no real title available?)
- Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized \varepsilon-Nash Equilibria
- Large-population LQG games involving a major player: the Nash certainty equivalence principle
- Mean field game theory with a partially observed major agent
- Mean field games
- Mean field games with a dominating player
- Mean field games. I: The stationary case
- Mean field games. II: Finite horizon and optimal control
- Nonlinear Filtering Theory for McKean--Vlasov Type Stochastic Differential Equations
- Nonlinear Semigroup for Controlled Partially Observed Diffusions
- On the Relation of Zakai’s and Mortensen’s Equations
- Probabilistic theory of mean field games with applications I. Mean field FBSDEs, control, and games
- Stochastic Hamilton–Jacobi–Bellman Equations
Cited in
(22)- The execution problem in finance with major and minor traders: a mean field game formulation
- Some partially observed multi-agent linear exponential quadratic stochastic differential games
- Secure discrete-time linear-quadratic mean-field games
- Maximum principle for general partial information nonzero sum stochastic differential games and applications
- Convex analysis for LQG systems with applications to major-minor LQG mean-field game systems
- Dynamic optimization of large-population systems with partial information
- Extended mean-field control problem with partial observation
- Approximate Nash equilibria in partially observed stochastic games with mean-field interactions
- Mean field game theory with a partially observed major agent
- Partially observed discrete-time risk-sensitive mean field games
- Linear-Quadratic Large-Population Problem with Partial Information: Hamiltonian Approach and Riccati Approach
- Second-order necessary condition for partially observed stochastic system with random jumps
- Incomplete information mean-field games and related Riccati equations
- Linear-quadratic mean-field game for stochastic systems with partial observation
- Linear-quadratic mean field Stackelberg stochastic differential game with partial information and common noise
- Near optimal approximations and finite memory policies for POMPDs with continuous spaces
- Bayesian learning in mean field games
- Mean field equilibrium asset pricing model under partial observation: an exponential quadratic Gaussian approach
- Closed-loop equilibria for mean-field games in randomly switching environments with general discounting costs
- -Nash equilibrium of anticipative large-population LQ game with partial observations
- Linear-quadratic Gaussian mixed leadership differential games with overlapping observation
- Linear-quadratic-Gaussian mean-field-game with partial observation and common noise
This page was built for publication: Mean Field Games with Partial Observation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5232215)
