Optimization Frameworks & Learning Algorithms for Discrete-Time Mean Field Games
Abstract
This monograph introduces discrete-time mean field games with finite state and action spaces, emphasizing optimization formulations and learning algorithms. Starting from Markov decision processes and finite-player stochastic games, it develops the notion of mean field Nash equilibrium, establishes existence and uniqueness results under suitable assumptions, and explains how mean field equilibria yield approximate equilibria in large finite-player games. Building on the linear programming formulation of Markov decision processes, occupation measures and primal-dual formulations connect equilibrium computation with mathematical optimization. The monograph presents fixed-point iterations, fictitious play, online mirror descent, and optimization-based methods, discussing their convergence properties and limitations. Numerical examples illustrate crowd motion, traffic routing, epidemic management, and the computation of multiple equilibria. It combines examples, theoretical results, and implementable algorithms, with bibliographic notes providing connections to the broader literature.
Related
- Variational Contraction Conditions for Iterative Algorithms in Multi-Population Discrete-Time Regularized Mean-Field Games
- Mean Field Reinforcement Learning: Theory and Algorithms for Mean Field Control
- Mean-Field PhiBE: Continuous-Time Mean-Field Reinforcement Learning from Discrete-Time Data
- A hybrid approach for steady-state production optimization of a real oil and gas platform: Integrating physics-based models, machine learning techniques, and field monitoring signals
- Learning Choice Model Trees for Feature-Based Multi-Product Pricing: Exact Optimization and Field Evidence
BibTeX
@misc{guo2026optimization,
title = {{Optimization Frameworks & Learning Algorithms for Discrete-Time Mean Field Games}},
author = {Xin Guo and Mathieu Laurière},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01754},
eprint = {2611.01754},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01754},
}
RIS
TY - UNPB
TI - Optimization Frameworks & Learning Algorithms for Discrete-Time Mean Field Games
AU - Xin Guo
AU - Mathieu Laurière
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01754
UR - https://arxiv.org/abs/2611.01754
AB - This monograph introduces discrete-time mean field games with finite state and action spaces, emphasizing optimization formulations and learning algorithms. Starting from Markov decision processes and finite-player stochastic games, it develops the notion of mean field Nash equilibrium, establishes existence and uniqueness results under suitable assumptions, and explains how mean field equilibria yield approximate equilibria in large finite-player games. Building on the linear programming formulation of Markov decision processes, occupation measures and primal-dual formulations connect equilibrium computation with mathematical optimization. The monograph presents fixed-point iterations, fictitious play, online mirror descent, and optimization-based methods, discussing their convergence properties and limitations. Numerical examples illustrate crowd motion, traffic routing, epidemic management, and the computation of multiple equilibria. It combines examples, theoretical results, and implementable algorithms, with bibliographic notes providing connections to the broader literature.
ER -