Abstract
This paper takes an overtly anticipatory stance to the understanding of animat learning and behavior. It analyses four major animal learning theories and attempts to identify the anticipatory and predictive elements inherent to them, and to provide a new unifying approach based on the anticipatory nature of those elements based on five simple predictive ”rules”. These rules encapsulate all the principal properties of the four diverse theories (the four factors) and provide a simple framework for understanding how an individual animat may appear to operate according to different principles under varying circumstances. The paper then indicates how these anticipatory principles can be used to define a more detailed set of postulates for the Dynamic Expectancy Model of animat learning and behavior, and to construct its computer implementation SRS/E. Some of the issues discussed are illustrated with an example experimental procedure using SRS/E
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Agre, P.E.: Computational Research on Interaction and Agency. Artificial Intelligence 72, 1–52 (1995)
Baird, L.C., Klopf, A.H.: Extensions to the Associative Control Process (ACP) Network: Hierarchies and Provable Optimality. In: 2nd Int. Conf. on Simulation of Adaptive Behavior (SAB-2), pp. 163–171 (1993)
Balkenius, C.: Natural Intelligence in Artificial Creatures, Lund University Cognitive Studies 37 (1995)
Balkenius, C., Morén, J.: Computational Models of Classical Conditioning: A Comparative Study. In: 5th Int. Conf. on Simulation of Adaptive Behavior (SAB-5), pp. 348–353 (1998)
Barto, A.G., Sutton, R.S.: Simulation of Anticipatory Responses in Classical Conditioning by a Neuron-like Adaptive Element. Behavioral Brain Research 4, 221–235 (1982)
Bower, G.H., Hilgard, E.R.: Theories of Learning, 5th edn. Prentice Hall Inc., Englewood Cliffs (1981)
Brooks, R.A.: Intelligence Without Reason, MIT AI Laboratory, A.I. Memo No. 1293 (Prepared for Computers and Thought). In: IJCAI 1991 (April 1991) (preprint)
Bryson, J.: Hierarchy and Sequence vs. Full Parallelism in Action Selection. In: 6th Int. Conf. on Simulation of Adaptive Behavior (SAB-6), pp. 147–156 (2000)
Butz, M.V., Sigaud, O., Gerard, P.: Internal Models and Anticipations in Adaptive Learning Systems. In: Adaptive Behavior in Anticipatory Learning Systems 2002 Workshop (ABiALS 2002), p. 23 (2002)
Catania, A.C.: The Operant Behaviorism of B.F. Skinner. In: Catania, A.C., Harnad, S. (eds.) The Selection of Behavior, pp. 3–8. Cambridge University Press, Cambridge (1988)
Maes, P.: Behavior-based Artificial Intelligence. In: 2nd Int. Conf. on Simulation of Adaptive Behavior (SAB-2), pp. 2–10 (1993)
Mowrer, O.H.: Two-factor Learning Theory Reconsidered, with Special Reference to Secondary Reinforcement and the Concept of Habit. Psychological Review 63, 114–128 (1956)
Rosenblatt, J.K., Payton, D.W.: A Fine-Grained Alternative to the Subsumption Architecture for Mobile Robot Control. In: IEEE/INNS Int. Joint Conf. on Neural Networks, vol. II, pp. 317–323 (1989)
Saksida, L.M., Raymond, S.M., Touretzky, D.S.: Shaping Robot Behavior Using Principles from Instrumental Conditioning. Robotics and Autonomous Systems 22-3/4, 231–249 (1997)
Schaffer, S.: Babbage.s Intelligence: Calculating Engines and the Factory System (1998), hosted at http://cci.wmin.ac.uk/schaffer/schaffer01.html
Schmajuk, N.A.: Behavioral Dynamics of Escape and Avoidance: A Neural Network Approach. In: 3rd Int. Conf. on Simulation of Adaptive Behavior (SAB-3), pp. 118-127 (1994)
Shettleworth, S.J.: Reinforcement and the Organization of Behavior in Golden Hamsters: Hunger, Environment, and Food Reinforcement. Journal of Experimental Psychology: Animal Behavior Processes 104-1, 56–87 (1975)
Stolzmann, W., Butz, M.V., Hoffmann, J., Goldberg, D.E.: First Cognitive Capabilities in the Anticipatory Classifier System. In: 6th Int. Conf. on Simulation of Adaptive Behavior (SAB-6), pp. 287-296 (2000)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tani, J., Nolfi, S.: Learning to Perceive the World as Articulated: An Approach for Hierarchical Learning in Sensory-Motor Systems. In: 5th Int. Conf. on Simulation of Adaptive Behavior (SAB-5), pp. 270–279 (1998)
Thistlethwaite, D.: A Critical Review of Latent Learning and Related Experiments. Psychological Bulletin 48(2), 97–129 (1951)
Thorndike, E.L.: Animal Intelligence: An Experimental Study of the Associative Processes in Animals. Psychol. Rev., Monogr. Suppl., 2-8 (1898)
Tolman, E.C.: Purposive Behavior in Animals and Men. The Century Co., New York (1932)
Tyrrell, T.: Computational Mechanisms for Action Selection, University of Edinburgh, Ph.D. thesis (1993)
Witkowski, M.: Dynamic Expectancy: An Approach to Behaviour Shaping Using a New Method of Reinforcement Learning. In: 6th Int. Symp. on Intelligent Robotic Systems, pp. 73–81 (1998)
Witkowski, M.: Integrating Unsupervised Learning, Motivation and Action Selection in an A-life Agent. In: Floreano, D., Mondada, F. (eds.) ECAL 1999. LNCS, vol. 1674, pp. 355–364. Springer, Heidelberg (1999)
Witkowski, M.: The Role of Behavioral Extinction in Animat Action Selection. In: 6th Int. Conf. on Simulation of Adaptive Behavior (SAB-6), pp. 177–186 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Witkowski, M. (2003). Towards a Four Factor Theory of Anticipatory Learning. In: Butz, M.V., Sigaud, O., Gérard, P. (eds) Anticipatory Behavior in Adaptive Learning Systems. Lecture Notes in Computer Science(), vol 2684. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45002-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-45002-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40429-3
Online ISBN: 978-3-540-45002-3
eBook Packages: Springer Book Archive