ZCS: A Zeroth Level Classifier System

被引:257
作者
Wilson, Stewart W. [1 ]
机构
[1] Rowland Inst Sci, Cambridge, MA 02142 USA
关键词
Classifier systems; Q-learning; temporary memory; action selection; restricted mating; s-classifiers; genetic programming;
D O I
10.1162/evco.1994.2.1.1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];
摘要
A basic classifier system, ZCS, is presented that keeps much of Holland's original framework but simplifies it to increase understandability and performance. ZCS's relation to Q-learning is brought out, and their performances compared in environments of two difficulty levels. Extensions to ZCS are proposed for temporary memory, better action selection, more efficient use of the genetic algorithm, and more general classifier representation.
引用
收藏
页码:1 / 18
页数:18
相关论文
共 35 条
[1]
[Anonymous], 1992, GENETIC PROGRAMMING
[2]
Barto A.G., 1992, HDB INTELLIGENT CONT
[3]
Booker L., 1982, THESIS U MICHIGAN AN
[4]
Booker L. B, 1991, FDN GENETIC ALGORITH, P115
[5]
BOOKER LB, 1989, PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON GENETIC ALGORITHMS, P265
[6]
Cliff Dave, 1993, Adaptive Behavior, V2, P49, DOI 10.1177/105971239300200103
[7]
Genetic and Non-Genetic Operators in ALECSYS [J].
Dorigo, Marco .
EVOLUTIONARY COMPUTATION, 1993, 1 (02) :151-164
[8]
FINDING STRUCTURE IN TIME [J].
ELMAN, JL .
COGNITIVE SCIENCE, 1990, 14 (02) :179-211
[9]
Grefenstette J. J., 1985, P 1 INT C GEN ALG TH, P16
[10]
Grefenstette John J., 1992, Adaptive Behavior, V1, P65, DOI 10.1177/105971239200100104