This book offers a comprehensive introduction to learning classifier systems (LCS) – or more generally, rule-based evolutionary online learning systems. LCSs learn interactively – much like a neural network – but with an increased adaptivity and flexibility. This book provides the necessary background knowledge on problem types, genetic algorithms, and reinforcement learning as well as a principled, modular analysis approach to understand, analyze, and design LCSs. The analysis is exemplarily carried through on the XCS classifier system – the currently most prominent system in LCS research. Several enhancements are introduced to XCS and evaluated. An application suite is provided including classification, reinforcement learning and data-mining problems. Reconsidering John Holland’s original vision, the book finally discusses the current potentials of LCSs for successful applications in cognitive science and related areas.
Rule-based evolutionary online learning systems, often referred to as Michiganstyle learning classifier systems (LCSs), were proposed nearly thirty years ago (Holland, 1976; Holland, 1977) originally calling them cognitive systems. LCSs combine the strength of reinforcement learning with the generalization capabilities of genetic algorithms promising a flexible, online generalizing, solely reinforcement dependent learning system. However, despite several initial successful applications of LCSs and their interesting relations with animal learning and cognition, understanding of the systems remained somewhat obscured. Questions concerning learning complexity or convergence remained unanswered. Performance in different problem types, problem structures, concept spaces, and hypothesis spaces stayed nearly unpredictable. This book has the following three major objectives: (1) to establish a facetwise theory approach for LCSs that promotes system analysis, understanding, and design; (2) to analyze, evaluate, and enhance the XCS classifier system (Wilson, 1995) by the means of the facetwise approach establishing a fundamental XCS learning theory; (3) to identify both the major advantages of an LCS-based learning approach as well as the most promising potential application areas. Achievingthese three objectives leads to a rigorous understanding of LCS functioning that enables the successful application of LCSs to diverse problem types and problem domains. The quantitative analysis of XCS shows that the interactive, evolutionary-based online learning mechanism works machine learning competitively yielding a low-order polynomial learning complexity. Moreover, the facetwise analysis approach facilitates the successful design of more advanced LCSs including Holland’s originally envisioned cognitive systems.