Structured Output Feedback Control for Linear Quadratic Regulator Using Policy Gradient Method

نویسندگان

چکیده

We consider the static output feedback control for Linear Quadratic Regulator problems with structured constraints under assumption that system parameters are unknown. To solve problem in model free setting, we propose policy gradient algorithm based on projection method and show its global convergence to $\varepsilon$ -stationary points. In addition, introduce a variance reduction technique both theoretically numerically it significantly reduces estimation. also numerical experiments approach efficiently solves problem.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Control System Design for a Surface Effect Ship by Linear-Quadratic Regulator Method

In this paper, the main goal is to reduce the heave motion between a surface effect ship (SES) and a wind turbine in order to safely transfer equipment and person to SES. For this purpose, an LQR control system is designed to damp the vertical motion of the surface effect ship in critical sea states including high-frequency and high amplitude regular waves as well as high frequency irregular wa...

متن کامل

Adaptive Linear Quadratic Control Using Policy Iteration

In this paper we present stability and convergence results for Dynamic Programming-based reinforcement learning applied to Linear Quadratic Regulation (LQR). The spe-ciic algorithm we analyze is based on Q-learning and it is proven to converge to the optimal controller provided that the underlying system is controllable and a particular signal vector is persistently excited. The performance of ...

متن کامل

Linear backstepping output feedback control for uncertain linear systems

This paper presents a variation on adaptive backstepping output feedback control design for uncertain minimum-phase linear systems. Unlike the traditional nonlinear design, the proposed control method is linear and Lyapunov-based without utilizing overparametrization, tuning functions, or nonlinear damping terms to address parameter estimation error. Local stability of the closed-loop system an...

متن کامل

LMI based output - feedback controllers : γ - optimal versus linear quadratic ⋆

Solution to the linear quadratic control problem is given in the class of linear dynamic output-feedback full order controllers. Necessary and sufficient conditions for existence of such an optimal controller are stated in terms of linear matrix inequalities provided that initial conditions for controller states to be zero. It is shown that parameters of the optimal controller depend on an init...

متن کامل

Linear Quadratic Control for Systems with Structured Uncertainty

The standard LQR design technique is extended to systems with parametric uncertainty in the open-loop "A" matrix. This design, called the robust LQR (RLQR), guarantees the stability of the uncertain system, and the same level of performance robustness as standard LQR designs. To determine the properties of the RLQR design, simulations are performed on various mass-spring systems, and compared t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Automatic Control

سال: 2023

ISSN: ['0018-9286', '1558-2523', '2334-3303']

DOI: https://doi.org/10.1109/tac.2023.3264176