Reinforcement learning control of nonlinear multi-link system

被引：19

作者：

Bucak, IO ^{[1
]}

Zohdy, MA ^{[1
]}

机构：

[1] Oakland Univ, Dept Elect & Syst Engn, Rochester, MI 48309 USA

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 2001年 / 14卷 / 05期

关键词：

reinforcement learning; learning control; nonlinear control; robotics; learning algorithm;

D O I：

10.1016/S0952-1976(01)00031-8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, the effects of basic parameters in reinforcement learning control such as eligibility, action and critic network constrained weights, system nonlinearities, gradient information, state-space partitioning, variance of exploration are studied in detail. It is attempted to increase feasibility for practical applications, implementation, learning efficiency, and enhance performance. Also, a novel adaptive grid algorithm is proposed to overcome the difficulty in partitioning the input space to achieve better performance. Reinforcement learning is applied for control of a nonlinear one and two-link robots. This problem dictates that the learning is performed on-line, based on a binary or real-valued reinforcement signal from a critic network, without knowing the system model or nonlinearity. (C) 2002 Elsevier Science Ltd. All rights reserved.

引用

页码：563 / 575

页数：13

共 16 条

[1]

Anderson C. W., 1989, IEEE Control Systems Magazine, V9, P31, DOI 10.1109/37.24809

[2]

Bertsekas D., 1996, NEURO DYNAMIC PROGRA, V1st

[3]

Bucack I. O., 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251), P1198, DOI 10.1109/ACC.1999.783230

[4]

Bucak IO, 1998, P AMER CONTR CONF, P1405, DOI 10.1109/ACC.1998.707055

[5] A self-learning fuzzy logic controller using genetic algorithms with reinforcements [J].

Chiang, CK ;

Chung, HY ;

Lin, JJ .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 1997, 5 (03) :460-467

[6]

COSTA EF, 1997, P AM CONTR C AM AUT

[7] A STOCHASTIC REINFORCEMENT LEARNING ALGORITHM FOR LEARNING REAL-VALUED FUNCTIONS [J].

GULLAPALLI, V .

NEURAL NETWORKS, 1990, 3 (06) :671-692

[8]

Gullapalli V., 1994, IEEE CONTROL SYSTEMS

[9]

HIRASHIMA Y, 1999, P 38 C DE CONTR IEEE

[10]

HIRZINGER G, 1996, IEEE ASME T MECHATRO, V1, P150

← 1 2 →