Convergence of deep fictitious play for stochastic differential games
Frontiers of Mathematical Finance · 2022 · 1 (2) · 287
DOI: 10.3934/fmf.2021011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers of Mathematical Finance, 2022. Verfasst von Jiequn Han und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 71 Literaturangaben.
Abstract (Originalsprache)
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 and efficient tool for finding Markovian Nash equilibrium of large \begin{document}$ N $\end{document}-player asymmetric stochastic differential games [J. Han and R. Hu, Mathematical and Scientific Machine Learning Conference, pages 221-245, PMLR, 2020]. By incorporating the idea of fictitious play, the algorithm decouples the game into \begin{document}$ N $\end{document} sub-optimization problems, and identifies each player's optimal strategy with the deep backward stochastic differential equation (BSDE) method parallelly and repeatedly. In this paper, we prove the convergence of deep fictitious play (DFP) to the true Nash equilibrium. We can also show that the strategy based on DFP forms an \begin{document}$ \epsilon $\end{document}-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.
Zitieren
APA
Han, J., Hu, R., & Long, J. (2022). Convergence of deep fictitious play for stochastic differential games. Frontiers of Mathematical Finance, 1(2), 287. https://doi.org/10.3934/fmf.2021011
Vancouver
Han J, Hu R, Long J. Convergence of deep fictitious play for stochastic differential games. Frontiers of Mathematical Finance. 2022;1(2):287. doi:10.3934/fmf.2021011
BibTeX
@article{Han2022,
author = {Han, Jiequn and Hu, Ruimeng and Long, Jihao},
title = {Convergence of deep fictitious play for stochastic differential games},
journal = {Frontiers of Mathematical Finance},
year = {2022},
volume = {1},
number = {2},
pages = {287},
doi = {10.3934/fmf.2021011}
}
EUVIMED