Model-free $H_{\infty}$ control of Itô stochastic system via off-policy reinforcement learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Guo, Jing Guo Jing, Jiang, Xiushan, Zhang, Weihai
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913257149693952
author Guo, Jing Guo Jing
Jiang, Xiushan
Zhang, Weihai
author_facet Guo, Jing Guo Jing
Jiang, Xiushan
Zhang, Weihai
contents The stochastic $H_{\infty}$ control is studied for a linear stochastic Itô system with an unknown system model. The linear stochastic $H_{\infty}$ control issue is known to be transformable into the problem of solving a so-called generalized algebraic Riccati equation (GARE), which is a nonlinear equation that is typically difficult to solve analytically. Worse, model-based techniques cannot be utilized to approximately solve a GARE when an accurate system model is unavailable or prohibitively expensive to construct in reality. To address these issues, an off-policy reinforcement learning (RL) approach is presented to learn the solution of a GARE from real system data rather than a system model; its convergence is demonstrated, and the robustness of RL to errors in the learning process is investigated. In the off-policy RL approach, the system data may be created with behavior policies rather than the target policies, which is highly significant and promising for use in actual systems. Finally, the proposed off-policy RL approach is validated on a stochastic linear F-16 aircraft system.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Model-free $H_{\infty}$ control of Itô stochastic system via off-policy reinforcement learning
Guo, Jing Guo Jing
Jiang, Xiushan
Zhang, Weihai
Optimization and Control
The stochastic $H_{\infty}$ control is studied for a linear stochastic Itô system with an unknown system model. The linear stochastic $H_{\infty}$ control issue is known to be transformable into the problem of solving a so-called generalized algebraic Riccati equation (GARE), which is a nonlinear equation that is typically difficult to solve analytically. Worse, model-based techniques cannot be utilized to approximately solve a GARE when an accurate system model is unavailable or prohibitively expensive to construct in reality. To address these issues, an off-policy reinforcement learning (RL) approach is presented to learn the solution of a GARE from real system data rather than a system model; its convergence is demonstrated, and the robustness of RL to errors in the learning process is investigated. In the off-policy RL approach, the system data may be created with behavior policies rather than the target policies, which is highly significant and promising for use in actual systems. Finally, the proposed off-policy RL approach is validated on a stochastic linear F-16 aircraft system.
title Model-free $H_{\infty}$ control of Itô stochastic system via off-policy reinforcement learning
topic Optimization and Control
url https://arxiv.org/abs/2403.04412