mlsanityData to 14 Oct 2026

Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations

arXiv 2504.13228 ↗First posted 17 Apr 2025cs.LG cs.GTcited by 0

Not on the map. Why?

Abstract (arXiv)

Mean-field game theory relies on approximating games that are intractable to model due to a very large to infinite population of players. While these kinds of games can be solved analytically via the associated system of partial derivatives, this approach is not model-free, can lead to the loss of the existence or uniqueness of solutions, and may suffer from modelling bias. To reduce the dependency between the model and the game, we introduce neural mean-field games: a combination of mean-field game theory and deep learning in the form of neural stochastic differential equations. The resulting model is data-driven, lightweight, and can learn extensive strategic interactions that are hard to capture using mean-field theory alone. In addition, the model is based on automatic differentiation, making it more robust and objective than approaches based on finite differences. We highlight the efficiency and flexibility of our approach by solving two mean-field games that vary in their complexity, observability, and the presence of noise. Lastly, we illustrate the model's robustness by simulating viral dynamics based on real-world data. Here, we demonstrate that the model's ability to learn from real-world data helps to accurately model the evolution of an epidemic outbreak. Using these results, we show that the model is flexible, generalizable, and requires few observations to learn the distribution underlying the data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 79 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

32 of 79 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  5. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 283
  6. 2022On Neural Differential Equationscited by 268
  7. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 176
  8. 2019Neural Jump Stochastic Differential Equationscited by 150
  9. 2021Equinox: neural networks in JAX via callable PyTrees and filtered transformationscited by 148
  10. 2019Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noisecited by 101
  11. 2021Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learningcited by 73
  12. 2021Efficient and Accurate Gradients for Neural SDEscited by 71
20 more
  1. 2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 63
  2. 2022Learning in Mean Field Games: A Surveycited by 61
  3. 2020Q-Learning in Regularized Mean-field Gamescited by 42
  4. 2022Scalable Deep Reinforcement Learning Algorithms for Mean Field Gamescited by 38
  5. 2020Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Gamescited by 35
  6. 2019Convergence Analysis of Machine Learning Algorithms for the Numerical Solution of Mean Field Control and Games: II -- The Finite Horizon Casecited by 34
  7. 2021Mean Field Games Flock! The Reinforcement Learning Waycited by 31
  8. 2022Neural Laplace: Learning diverse classes of differential equations in the Laplace domaincited by 24
  9. 2020Mean Field Games and Applications: Numerical Aspectscited by 22
  10. 2023Actor-Critic learning for mean-field control in continuous timecited by 22
  11. 2019Infinitely deep neural networks as diffusion processescited by 21
  12. 2020Partially Observable Mean Field Reinforcement Learningcited by 16
  13. 2022Neural parameter calibration for large-scale multi-agent modelscited by 14
  14. 2018On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplingscited by 9
  15. 2024Individual vaccination as Nash equilibrium in a SIR model with application to the 2009-10 Influenza A(H1N1) epidemic in Francecited by 3
  16. 2019Discrete Mean Field Games: Existence of Equilibria and Convergencecited by 2
  17. 2023Deep Policy Iteration for High-Dimensional Mean Field Gamescited by 2
  18. 2018Modeling tagged pedestrian motion: a mean-field type game approachcited by 1
  19. 2021A Game-Theoretic Approach for Hierarchical Epidemic Controlcited by 1
  20. 2023Deep Learning for Mean Field Games with non-separable Hamiltonianscited by 1

Built on by

Not cited yet.