Adaptive linear quadratic control using policyiterationSteven

نویسندگان

  • Steven J. Bradtke
  • B. Erik Ydstie
  • Andrew G. Barto
چکیده

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 the algorithm is illustrated by applying it to a model of a exible beam.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Adaptive Predictive Controllers Using a Growing and Pruning RBF Neural Network

An adaptive version of growing and pruning RBF neural network has been used to predict the system output and implement Linear Model-Based Predictive Controller (LMPC) and Non-linear Model-based Predictive Controller (NMPC) strategies. A radial-basis neural network with growing and pruning capabilities is introduced to carry out on-line model identification.An Unscented Kal...

متن کامل

Haar Matrix Equations for Solving Time-Variant Linear-Quadratic Optimal Control Problems

‎In this paper‎, ‎Haar wavelets are performed for solving continuous time-variant linear-quadratic optimal control problems‎. ‎Firstly‎, ‎using necessary conditions for optimality‎, ‎the problem is changed into a two-boundary value problem (TBVP)‎. ‎Next‎, ‎Haar wavelets are applied for converting the TBVP‎, ‎as a system of differential equations‎, ‎in to a system of matrix algebraic equations‎...

متن کامل

Discrete-time repetitive optimal control: Robotic manipulators

This paper proposes a discrete-time repetitive optimal control of electrically driven robotic manipulators using an uncertainty estimator. The proposed control method can be used for performing repetitive motion, which covers many industrial applications of robotic manipulators. This kind of control law is in the class of torque-based control in which the joint torques are generated by permanen...

متن کامل

Adaptive continuous-time linear quadratic Gaussian control

The adaptive linear quadratic Gaussian control problem, where the linear transformation of the state A and the linear transformation of the control B are unknown, is solved assuming only that (A; B) is controllable and (A; Q 1 ) is observable, where Q 1 determines the quadratic form for the state in the integrand of the cost functional. A weighted least squares algorithm is modified by using a ...

متن کامل

Comparison of Adaptive Vibration Control Techniques for Smart Structures using Virtual Instrumentation software LAB-VIEW

s--By making the controller adaptive, ideal performance and granted stability of the closed loop system can be achieved for even a large change in system parameters. In the present study, adaptive controllers based on minimum variance, pole placement and linear quadratic techniques are investigated. The controller based on minimum variance is noise sensitive and actuator voltage changes sign af...

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

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994