Saved in:
Bibliographic Details
Main Authors: Li, Dongdong, Dong, Jiuxiang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.20845
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910882786705408
author Li, Dongdong
Dong, Jiuxiang
author_facet Li, Dongdong
Dong, Jiuxiang
contents Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement and achieve model-free optimal control, in this paper, two different reinforcement learning algorithms based on policy iteration and variable damping coefficients are designed for unknown discrete-time linear systems. First, a stable artificial system is designed, and this system is gradually iterated to the original system by varying the damping coefficients. This allows the initial stabilizing control to be obtained in a finite number of iteration steps. Then, an off-policy iteration algorithm and an off-policy $\mathcal{Q}$-learning algorithm are designed to select the appropriate damping coefficients and realize data-driven. In these two algorithms, the current estimates of optimal control gain are not applied to the system to re-collect data. Moreover, they are characterized by the fast convergence of the traditional policy iteration. Finally, the proposed algorithms are validated by simulation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data-Based Efficient Off-Policy Stabilizing Optimal Control Algorithms for Discrete-Time Linear Systems via Damping Coefficients
Li, Dongdong
Dong, Jiuxiang
Systems and Control
Policy iteration is one of the classical frameworks of reinforcement learning, which requires a known initial stabilizing control. However, finding the initial stabilizing control depends on the known system model. To relax this requirement and achieve model-free optimal control, in this paper, two different reinforcement learning algorithms based on policy iteration and variable damping coefficients are designed for unknown discrete-time linear systems. First, a stable artificial system is designed, and this system is gradually iterated to the original system by varying the damping coefficients. This allows the initial stabilizing control to be obtained in a finite number of iteration steps. Then, an off-policy iteration algorithm and an off-policy $\mathcal{Q}$-learning algorithm are designed to select the appropriate damping coefficients and realize data-driven. In these two algorithms, the current estimates of optimal control gain are not applied to the system to re-collect data. Moreover, they are characterized by the fast convergence of the traditional policy iteration. Finally, the proposed algorithms are validated by simulation.
title Data-Based Efficient Off-Policy Stabilizing Optimal Control Algorithms for Discrete-Time Linear Systems via Damping Coefficients
topic Systems and Control
url https://arxiv.org/abs/2412.20845