Anticipatory Behavior in Adaptive Learning Systems: Foundations, Theories, and SystemsMartin V. Butz, Olivier Sigaud, Pierre Gérard The matter of anticipation is, as the editors of this volume state in their preface, a rathernewtopic. Giventhealmostconstantusewemakeofanticipationin our dailyliving, itseemsoddthatthebulk ofpsychologistshavepersistentlyignored it. However, the reason for this disregard is not di'cult to ?nd. The dogma of the scienti'c revolution had from the outset laid down the principle that future conditions and events could not in'uence the present. The law of causation clearly demands that causes should precedetheir e'ects and, therefore, concepts such as purpose, anticipation, and even intention were taboo because they were thought to involve things and happenings that lay ahead in time. An analysis of the three concepts - purpose, anticipation, and intention - shows that they are rooted in the past and transcend the present only insofar as they contain mental representations of things to be striven for or avoided. Purposiveorgoal-directedactioncouldbe circumscribedasactioncarriedoutto attain something desirable. In each case, the particular action is chosenbecause, in the past, it has more or less reliably led to the desired end. The only way the future is involved in this procedure is through the belief that the experiential worldmanifestssomeregularityandallowsthelivingorganismtoanticipatethat what has workedin the past will continue to work in the future. This belief does not have to be conscious. Skinner's rats continued to turn left in a maze where theleftarmhadbeenbaited. Theydidsobecausethemeatpelletthey foundthe rst time had "reinforced" them to repeat the turn to the left. |
Contents
Introduction | 1 |
Systems Evaluations and Applications | 4 |
Not Everything We Know We Learned | 23 |
From Cognitive Psychology to Cognitive Systems | 44 |
Towards a Four Factor Theory of Anticipatory Learning | 66 |
Formulations Distinctions and Characteristics | 86 |
Mathematical Foundations of Discrete and Functional Systems with Strong | 110 |
Building on Lewin | 133 |
Revisiting a Robot | 167 |
Forward and Bidirectional Planning Based on Reinforcement Learning | 179 |
Sensory Anticipation for Autonomous Selection of Robot Landmarks | 201 |
Representing RobotEnvironment Interactions by Dynamical Features | 222 |
Anticipatory Guidance of Plot | 243 |
Exploring the Value of Prediction in an Artificial Stock Market | 262 |
Generalized State Values in an Anticipatory Learning Classifier System | 282 |
A Framework for Preventive State Anticipation | 151 |
Other editions - View all
Common terms and phrases
action active actual adaptive agent algorithm animal animat anticipation anticipatory behavior anticipatory system applied approach architecture associated basic become classical conditioning classifier cognitive complex Computing concept connection consequence considered context corresponding decision defined dependent described desired determined direction dynamic effects emotion environment equation evaluations example execution expected experimental experiments expression Figure framework function further future given goal human implementation important initial input Intelligence interaction internal knowledge landmark learning means mechanisms methods motivation move movements nature neural observed outcome output particular past path perception performance personality planning position possible predictive predictive model present Press problem properties Psychology reach reactive reinforcement relations representation represented response result reward robot rules selection sensory sequence shows Sign similar simulation situation step structure takes task theory tion understanding updates