期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 45, 期 2, 页码 165-176出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2014.2322116
关键词
Approximate dynamic programming (ADP); continuous-time dynamical systems; infinite-horizon discounted cost function; integral reinforcement learning (IRL); optimal control; Q-learning; value iteration (VI)
类别
资金
- Indo-U.S. Science and Technology Forum (IUSSTF), New Delhi, INDIA, under NSF Grant [ECCS-1128050, IIS-1208623]
- AFOSR EOARD [13-3055]
- China NNSF Grant [61120106011]
- China Education Ministry Project 111 [B08015]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1208623] Funding Source: National Science Foundation
- Div Of Electrical, Commun & Cyber Sys
- Directorate For Engineering [1128050, 1405173] Funding Source: National Science Foundation
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据