Title :
Learning to predict with the Delayed Action Classifier System
Author :
Carse, Brian ; Pipe, Anthony G.
Author_Institution :
Intelligent Autonomous Syst. Lab., West of England Univ., Bristol, UK
Abstract :
This paper describes an extended version of the Delayed Action Classifier System (DACS), a rule-based system which employs the genetic algorithm to discover temporal rules for learning in environments with temporal structure. The extended version of DACS (called DACS2) is described and experimentally evaluated. A mathematical analysis is provided which offers a theoretical justification of the advantages of DACS compared to non-temporal classifier systems. Areas for further development are briefly discussed and possible applications of the system in the field of intelligent control are suggested.
Keywords :
genetic algorithms; intelligent control; learning (artificial intelligence); mathematical analysis; temporal reasoning; DACS2; delayed action classifier system; genetic algorithm; intelligent control; learning; mathematical analysis; nontemporal classifier systems; rule based system; temporal rules; temporal structure;
Conference_Titel :
Intelligent Control. 2003 IEEE International Symposium on
Conference_Location :
Houston, TX, USA
Print_ISBN :
0-7803-7891-1
DOI :
10.1109/ISIC.2003.1253920
