Convergence of Deep Fictitious Play for Stochastic Differential Games

Abstract

Stochastic differential games have been used extensively to model agents' competitions in Finance, for instance, in P2P lending platforms from the Fintech industry, the banking system for systemic risk, and insurance markets. The recently proposed machine learning algorithm, deep fictitious play, provides a novel efficient tool for finding Markovian Nash equilibrium of large $N$-player asymmetric stochastic differential games [J. Han and R. Hu, Mathematical and Scientific Machine Learning Conference, pages 221-245, PMLR, 2020]. By incorporating the idea of fictitious play, the algorithm decouples the game into $N$ sub-optimization problems, and identifies each player's optimal strategy with the deep backward stochastic differential equation (BSDE) method parallelly and repeatedly. In this paper, we prove the convergence of deep fictitious play (DFP) to the true Nash equilibrium. We can also show that the strategy based on DFP forms an $\eps$-Nash equilibrium. We generalize the algorithm by proposing a new approach to decouple the games, and present numerical results of large population games showing the empirical convergence of the algorithm beyond the technical assumptions in the theorems.

References in corpus (11)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DGM: A deep learning algorithm for solving partial differential equations
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Convergence of the Deep BSDE Method for Coupled FBSDEs
• Training robust neural networks using Lipschitz bounds
• Deep splitting method for parabolic PDEs
• Deep Learning Approximation for Stochastic Control Problems
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games
• Deep Fictitious Play for Stochastic Differential Games
• Deep-learning based numerical BSDE method for barrier options

Cited by in corpus (7)

• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• An overview on deep learning-based approximation methods for partial differential equations
• Actor-Critic Method for High Dimensional Static Hamilton--Jacobi--Bellman Partial Differential Equations based on Neural Networks
• Neural networks-based algorithms for stochastic control and PDEs in finance
• Deep Fictitious Play for Stochastic Differential Games
• Optimal Policies for a Pandemic: A Stochastic Game Approach and a Deep Learning Algorithm
• Signatured Deep Fictitious Play for Mean Field Games with Common Noise