Abstract
The Anticipatory Classifier System (ACS) is a learning classifier system (LCS) that uses a learning process derived from psychology, which is called Anticipatory Learning Process (ALP). Besides the well known reward learning in LCS, the ACS is able to learn a model of its environment by using the ALP. The internal model of the environment consists of condition-action-effect rules. A typical question is LCS research is whether the rules are accurate and maximally general, i.e., whether the rules can be applied in a maximum number of situation. Latest research observed that the ACS is not generating accurate, maximally general rules reliably, but sometimes produces over-specialized rules. A genetic algorithm is used to overcome this pressure of over-specialization. This invited paper gives an introduction to the current version of ACS. Applications are not discussed. They can be found in “Anticipatory Classifier Systems: An Overview of Applications” (this volume).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.