Continuous-Time Q-Learning for Infinite-Horizon Discounted Cost Linear Quadratic Regulator Problems
This paper presents a method of Q-learning to solve the discounted linear quadratic regulator (LQR) problem for continuous-time (CT) continuous-state systems. Most available methods in the existing literature for CT systems to solve the LQR problem generally need partial or complete knowledge of the system dynamics. Q-learning is effective for unknown dynamical systems, but has generally been well understood only for discrete-time systems. The contribution of this paper is to present a Q-learning methodology for CT systems which solves the LQR problem without having any knowledge of the system dynamics. A natural and rigorous justified parameterization of the Q-function is given in terms of the state, the control input, and its derivatives. This parameterization allows the implementation of an online Q-learning algorithm for CT systems. The simulation results supporting the theoretical development are also presented.
M. Palanisamy et al., "Continuous-Time Q-Learning for Infinite-Horizon Discounted Cost Linear Quadratic Regulator Problems," IEEE Transactions on Cybernetics, vol. 45, no. 2, pp. 165-176, Institute of Electrical and Electronics Engineers (IEEE), Feb 2015.
The definitive version is available at http://dx.doi.org/10.1109/TCYB.2014.2322116
Electrical and Computer Engineering
Keywords and Phrases
Cost Functions; Digital Control Systems; Discrete Time Control Systems; Dynamic Programming; Dynamical Systems; Iterative Methods; Learning Algorithms; Online Systems; Problem Solving; Reinforcement Learning; System Theory; Approximate Dynamic Programming; Continuous Time Dynamical System; Infinite Horizon Discounted Costs; Integral Reinforcement Learning (IRL); Optimal Controls; Q-Learning; Value Iteration; Continuous Time Systems; Approximate Dynamic Programming (ADP); Continuous-Time Dynamical Systems; Infinite-Horizon Discounted Cost Function; Optimal Control; Value Iteration (VI)
International Standard Serial Number (ISSN)
Article - Journal
© 2015 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.