Anticipatory Learning Classifier Systems describes the state of the art of anticipatory learning classifier systems-adaptive rule learning systems that autonomously build anticipatory environmental models. An anticipatory model specifies all possible action-effects in an environment with respect to given situations. It can be used to simulate anticipatory adaptive behavior. Anticipatory Learning Classifier Systems highlights how anticipations influence cognitive systems and illustrates the use of anticipations for (1) faster reactivity, (2) adaptive behavior beyond reinforcement learning, (3) attentional mechanisms, (4) simulation of other agents and (5) the implementation of a motivational module. The book focuses on a particular evolutionary model learning mechanism, a combination of a directed specializing mechanism and a genetic generalizing mechanism. Experiments show that anticipatory adaptive behavior can be simulated by exploiting the evolving anticipatory model for even faster model learning, planning applications, and adaptive behavior beyond reinforcement learning. Anticipatory Learning Classifier Systems gives a detailed algorithmic description as well as a program documentation of a C++ implementation of the system.

Rule-basedevolutionaryonlinelearningsystems, oftenreferredtoasMichig- style learning classi?er 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 generali- tion capabilities of genetic algorithms promising a ?exible, online general- ing, solely reinforcement dependent learning system. However, despite several initial successful applications of LCSs and their interesting relations with a- mal learning and cognition, understanding of the systems remained somewhat obscured. Questions concerning learning complexity or convergence remained unanswered. Performance in di?erent problem types, problem structures, c- ceptspaces, andhypothesisspacesstayednearlyunpredictable. Thisbookhas the following three major objectives: (1) to establish a facetwise theory - proachforLCSsthatpromotessystemanalysis, understanding, anddesign;(2) to analyze, evaluate, and enhance the XCS classi?er 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. Achieving these 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 inter- tive, 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 - vanced LCSs including Holland's originally envisioned cognitive systems. Martin V.

Anticipatory behavior in adaptive learning systems continues attracting attention of researchers in many areas, including cognitive systems, neuroscience, psychology, and machine learning. This book constitutes the thoroughly refereed post-workshop proceedings of the 4th International Workshop on Anticipatory Behavior in Adaptive Learning Systems, ABiALS 2008, held in Munich, Germany, in June 2008, in collaboration with the six-monthly Meeting of euCognition 'The Role of Anticipation in Cognition'. The 18 revised full papers presented were carefully selected during two rounds of reviewing and improvement for inclusion in the book. The introductory chapter of this state-of-the-art survey not only provides an overview of the contributions included in this volume but also revisits the current available terminology on anticipatory behavior and relates it to the available system approaches. The papers are organized in topical sections on anticipation in psychology with focus on the ideomotor view, conceptualizations, anticipation and dynamical systems, computational modeling of psychological processes in the individual and social domains, behavioral and cognitive capabilities based on anticipation, and computational frameworks and algorithms for anticipation, and their evaluation.

This volume includes extended and revised versions of the papers presented at the 9th and 10th International Workshops on Learning Classi?er Systems (IWLCS 2006 and IWLCS 2007). Both workshops were held in association with theGeneticandEvolutionaryComputationConference(GECCO).IWLCS2006 was held on July 8th, 2006, in Seattle, USA, during GECCO 2006.IWLCS 2007 was held on July 8th, 2007, in London, UK, during GECCO 2007. The IWLCS is the annual meeting of researchers wishing to discuss recent developments in learning classi?er systems (LCS). At the last IWLCS, the LCS researchers commemorated the 10th anniversary of the workshop and ackno- edged the contribution of Stewart Wilson to the ?eld. Following his proposal of the XCS classi?er system in 1995, research on LCS was reactivated leading to signi?cant contributions and promising perspectives. The annual IWLCS wo- shops are the proof of this fruitful research. We include an invited paper from Stewart Wilson. We greatly appreciate his contribution to the volume. The contents of this book are as follows. First, Bacardit, Bernado -Mansilla and Butz review LCS research over the past ten years and point out new ch- lenges and open issues in the LCS ?eld. Next, papers investigating knowledge representations are presented. Lanzi et al. analyze the evolution of XCS with symbolic representations using a novel method that identi?es useful substr- tures and tracks the emergence of optimal solutions. Ioannides and Browne investigate the scaling of LCSs using ternary and symbolic representations."

The general idea that brains anticipate the future, that they engage in prediction, and that one means of doing this is through some sort of inner model that can be run of?ine, hasalonghistory. SomeversionoftheideawascommontoAristotle, aswell as to many medieval scholastics, to Leibniz and Hume, and in more recent times, to Kenneth Craik and Philip Johnson-Laird. One reason that this general idea recurs continually is that this is the kind of picture that introspection paints. When we are engaged in tasks it seems that we form images that are predictions, or anticipations, and that these images are isomorphic to what they represent. But as much as the general idea recurs, opposition to it also recurs. The idea has never been widely accepted, or uncontroversial among psychologists, cognitive scientists and neuroscientists. The main reason has been that science cannot be s- is?ed with metaphors and introspection. In order to gain acceptance, an idea needs to be formulated clearly enough so that it can be used to construct testable hypot- ses whose results will clearly supportor cast doubtupon the hypothesis. Next, those ideasthatare formulablein one oranothersortof symbolismor notationare capable of being modeled, and modeling is a huge part of cognitive neuroscience. If an idea cannot be clearly modeled, then there are limits to how widely it can be tested and accepted by a cognitive neuroscience communit

This book presents the refereed post-proceedings of the Third International Workshop on Anticipatory Behavior in Adaptive Learning Systems. Twenty full papers were chosen from among the many submissions. Papers are organized into sections covering anticipatory aspects in brains, language, and cognition; individual anticipatory frameworks; learning predictions and anticipations; anticipatory individual behavior; and anticipatory social behavior.

Rule-basedevolutionaryonlinelearningsystems, oftenreferredtoasMichig- style learning classi?er 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 generali- tion capabilities of genetic algorithms promising a ?exible, online general- ing, solely reinforcement dependent learning system. However, despite several initial successful applications of LCSs and their interesting relations with a- mal learning and cognition, understanding of the systems remained somewhat obscured. Questions concerning learning complexity or convergence remained unanswered. Performance in di?erent problem types, problem structures, c- ceptspaces, andhypothesisspacesstayednearlyunpredictable. Thisbookhas the following three major objectives: (1) to establish a facetwise theory - proachforLCSsthatpromotessystemanalysis, understanding, anddesign;(2) to analyze, evaluate, and enhance the XCS classi?er 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. Achieving these 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 inter- tive, 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 - vanced LCSs including Holland's originally envisioned cognitive systems. Martin V.

The interdisciplinary topic of anticipation, attracting attention from computer scientists, psychologists, philosophers, neuroscientists, and biologists is a rather new and often misunderstood matter of research. This book attempts to establish anticipation as a research topic and encourage further research and development work. First, the book presents philosophical thoughts and concepts to stimulate the reader's concern about the topic. Fundamental cognitive psychology experiments then confirm the existence of anticipatory behavior in animals and humans and outline a first framework of anticipatory learning and behavior. Next, several distinctions and frameworks of anticipatory processes are discussed, including first implementations of these concepts. Finally, several anticipatory systems and studies on anticipatory behavior are presented.

Anticipatory Learning Classifier Systems describes the state of the art of anticipatory learning classifier systems-adaptive rule learning systems that autonomously build anticipatory environmental models. An anticipatory model specifies all possible action-effects in an environment with respect to given situations. It can be used to simulate anticipatory adaptive behavior.

Anticipatory Learning Classifier Systems highlights how anticipations influence cognitive systems and illustrates the use of anticipations for (1) faster reactivity, (2) adaptive behavior beyond reinforcement learning, (3) attentional mechanisms, (4) simulation of other agents and (5) the implementation of a motivational module. The book focuses on a particular evolutionary model learning mechanism, a combination of a directed specializing mechanism and a genetic generalizing mechanism. Experiments show that anticipatory adaptive behavior can be simulated by exploiting the evolving anticipatory model for even faster model learning, planning applications, and adaptive behavior beyond reinforcement learning.

Anticipatory Learning Classifier Systems gives a detailed algorithmic description as well as a program documentation of a C++ implementation of the system. It is an excellent reference for researchers interested in adaptive behavior and machine learning from a cognitive science perspective as well as those who are interested in combining evolutionary learning mechanisms for learning and optimization tasks.