Rates of convergence for the policy iteration method for mean field games systems
From MaRDI portal
Publication:831502
DOI10.1016/j.jmaa.2022.126138zbMath1485.91019arXiv2108.00755OpenAlexW3190367256MaRDI QIDQ831502
Publication date: 23 March 2022
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2108.00755
Mean field games and control (49N80) Mean field games (aspects of game theory) (91A16) Hamilton-Jacobi equations in optimal control and differential games (49L12)
Related Items
Generalized conditional gradient and learning in potential mean field games, Policy iteration method for time-dependent mean field games systems with non-separable Hamiltonians, Learning Optimal Policies in Potential Mean Field Games: Smoothed Policy Iteration Algorithms
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Mean field games
- On the convergence of policy iteration for controlled diffusions
- Lipschitz regularity for viscous Hamilton-Jacobi equations with \(L^p\) terms
- Optimal control of conditioned processes with feedback controls
- Learning in mean field games: The fictitious play
- A policy iteration method for mean field games
- An Efficient Policy Iteration Algorithm for Dynamic Programming Equations
- Fokker–Planck–Kolmogorov Equations
- Global Properties of Transition Probabilities of Singular Diffusions
- Some Convergence Results for Howard's Algorithm
- On the Convergence of Policy Iteration in Stationary Dynamic Programming
- Proximal Methods for Stationary Mean Field Games with Local Couplings
- Convergence Properties of Policy Iteration
- Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions
- Large-Population Cost-Coupled LQG Problems With Nonuniform Agents: Individual-Mass Behavior and Decentralized $\varepsilon$-Nash Equilibria
- Mean Field Games and Mean Field Type Control Theory
- On L p Estimates and Regularity, I
