Saved in:
Bibliographic Details
Main Authors: Wei, Xiaoli, Yu, Xiang, Yuan, Fengyi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.04521
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910887519977472
author Wei, Xiaoli
Yu, Xiang
Yuan, Fengyi
author_facet Wei, Xiaoli
Yu, Xiang
Yuan, Fengyi
contents This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task to solve the MFG or MFC problem, we can employ the decoupled Iq-function differently to characterize the mean-field equilibrium policy or the mean-field optimal policy respectively. Based on these theoretical findings, we devise a unified q-learning algorithm for both MFG and MFC problems by utilizing test policies and the averaged martingale orthogonality condition. For several financial applications in the jump-diffusion setting, we obtain the exact parameterization of the decoupled Iq-functions and the value functions, and illustrate our q-learning algorithm with satisfactory performance.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04521
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unified continuous-time q-learning for mean-field game and mean-field control problems
Wei, Xiaoli
Yu, Xiang
Yuan, Fengyi
Optimization and Control
Machine Learning
Computational Finance
This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task to solve the MFG or MFC problem, we can employ the decoupled Iq-function differently to characterize the mean-field equilibrium policy or the mean-field optimal policy respectively. Based on these theoretical findings, we devise a unified q-learning algorithm for both MFG and MFC problems by utilizing test policies and the averaged martingale orthogonality condition. For several financial applications in the jump-diffusion setting, we obtain the exact parameterization of the decoupled Iq-functions and the value functions, and illustrate our q-learning algorithm with satisfactory performance.
title Unified continuous-time q-learning for mean-field game and mean-field control problems
topic Optimization and Control
Machine Learning
Computational Finance
url https://arxiv.org/abs/2407.04521