I am pleased to share with you that the Journal of Artificial Evolution and Applications has recently published my LCS Review paper entitled, “Learning Classifier Systems: A Complete Introduction, Review, and Roadmap”. I wrote this from the perspective of a non-computer scientist, to introduce the basic LCS concept, as well as the variation represented in different LCS implementations that have been tasked to different problem domains. It was my goal and hope that this review might provide a reasonable starting point for outsiders interested in understanding or getting involved in the LCS community. This paper may be viewed using the following link: Thanks! I enjoyed listening to the many excellent GBML talks given at GECCO this year.
Category: Articles
A list of relevant publications, including articles and the like
Classifier Fitness Based on Accuracy
In many classifier systems, the classifier strength parameter serves as a predictor of future payoff and as the classifier’s fitness for the genetic algorithm. We investigate a classifier system, XCS, in which each classifier maintains a prediction of expected payoff, but the classifier’s fitness is given by a measure of the prediction’s accuracy. The system executes the genetic algorithm in niches defined by the match sets, instead of panmictically. These aspects of XCS result in its population tending to form a complete and accurate mapping X x A => P from inputs and actions to payoff predictions. Further, XCS tends to evolve classifiers that are maximally general subject to an accuracy criterion. Besides introducing a new direction for classifier system research, these properties of XCS make it suitable for a wide range of reinforcement learning situations where generalization over states is desirable.
The paper can be downloaded at: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.6508