A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Peng, Xianhua, Kou, Steven, Zhang, Lekang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909418053959680
author Peng, Xianhua
Kou, Steven
Zhang, Lekang
author_facet Peng, Xianhua
Kou, Steven
Zhang, Lekang
contents We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve high-dimensional (e.g., over 100 dimensions) and finite-horizon time-inhomogeneous stochastic control problems. (2) It has a monotonicity of performance improvement in each iteration, leading to good convergence properties. (3) It does not rely on the Bellman equation. To demonstrate the efficiency of the algorithm, it is applied to solve various finite-horizon time-inhomogeneous problems including recursive utility optimization under a stochastic volatility model, a multi-sector stochastic growth, and optimal control under a dynamic stochastic integration of climate and economy model with eight-dimensional state vectors and 600 time periods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08668
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics
Peng, Xianhua
Kou, Steven
Zhang, Lekang
General Economics
Economics
Optimization and Control
Machine Learning
We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve high-dimensional (e.g., over 100 dimensions) and finite-horizon time-inhomogeneous stochastic control problems. (2) It has a monotonicity of performance improvement in each iteration, leading to good convergence properties. (3) It does not rely on the Bellman equation. To demonstrate the efficiency of the algorithm, it is applied to solve various finite-horizon time-inhomogeneous problems including recursive utility optimization under a stochastic volatility model, a multi-sector stochastic growth, and optimal control under a dynamic stochastic integration of climate and economy model with eight-dimensional state vectors and 600 time periods.
title A Machine Learning Algorithm for Finite-Horizon Stochastic Control Problems in Economics
topic General Economics
Economics
Optimization and Control
Machine Learning
url https://arxiv.org/abs/2411.08668