Comparisons of continuous-time and discrete-time Q-learning schemes for adaptive linear quadratic control

In this paper, we compare two online model-free Q-learning schemes for adaptive linear quadratic (LQ) control of discrete-time (DT) and continuous-time (CT) dynamical systems. Both Q-learning schemes come from the optimality principles, but the DT and CT Q-learning is designed with different Q-funct...

Full description

Saved in:
Bibliographic Details
Main Authors: Tae Yoon Chun, Jae Young Lee, Jin Bae Park, Yoon Ho Choi
Format: Conference Proceeding
Language:English
Subjects:
Convergence
DC motors
Educational institutions
Equations
g-learning
Heuristic algorithms
LQR
Numerical simulation
policy iteration
reinforcement learning
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we compare two online model-free Q-learning schemes for adaptive linear quadratic (LQ) control of discrete-time (DT) and continuous-time (CT) dynamical systems. Both Q-learning schemes come from the optimality principles, but the DT and CT Q-learning is designed with different Q-functions. This difference may results in the different exploration properties and convergence speeds. Numerical simulations with an ideal DC motor are carried out to further investigate and compare the Q-learning methods.