Abstract
The extent to which concepts, memory, and planning are necessary to the simulation of intelligent behavior is a fundamental philosophical issue in Artificial Intelligence. An active and productive segement of the AI community has taken the position that multiple low-level agents, properly organized, can account for high-level behavior. Empirical research on these questions with fully operational systems has been restricted to mobile robots that do simple tasks. This paper recounts experiments with Hoyle, a system in a cerebral, rather than a physical, domain. The program learns to perform well and quickly, often outpacing its human creators at two-person, perfect information board games. Hoyle demonstrates that a surprising amount of intelligent behavior can be treated as if it were situation-determined, that often planning is unnecessary, and that the memory required to support this learning is minimal. Concepts, however, are crucial to this reactive program's ability to learn and perform.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amarel, S. (1968), ‘On Representations of Problems of Reasoning about Actions’, in D. Michie, ed.,Machine Intelligence 3, Edinburgh: Edinburgh University Press, pp. 131–171.
Anantharaman, T., Campbell, M.S. and Hsu, F.-H. (1990), ‘Singular Extensions: Adding Selectivity to Brute-Force Searching’,Artificial Intelligence 43, pp. 99–110.
Baerends, G. P. (1976), ‘The Functional Organization of Behavior’,Animal Behavior 24, pp. 726–735.
Bell, R. C. (1969),Board and Table Games from Many Civilizations, London: Oxford University Press.
Berliner, H. and Ebeling, C. (1989), ‘Pattern Knowledge and Search: The SUPREM Architecture’,Artificial Intelligence 38, pp. 161–198.
Blakeslee, S. (1991), ‘Brain Yields New Clues on Its Organization for Language’, New York: The New York Times, September 10, 1991, p. C1.
Brooks, R. A. (1991), ‘Intelligence without Representation’,Artificial Intelligence 47, pp. 139–160.
Campbell, M. S. (1988), ‘Chunking as an Abstraction Mechanism’, Ph.D. Thesis, Carnegie Mellon.
Cobb, H.G. and Grefenstette, J. J. (1991), ‘Learning the Persistence of Actions in Reactive Control Rules’,Proceedings of the Eighth International Machine Learning Workshop, pp. 293–297.
Connell, J. (1990),Minimalist Mobile Robotics: A Colony-Style Architecture for an Artificial Creature, New York: Academic Press.
D'Andrade, R. G. (1990), ‘Some Propositions about the Relations between Culture and Human Cognition’, in J. W. Stigler, R. A. Shweder, and G. Herdt, eds.,Cultural Psychology: Essays on Comparative Human Development, Cambridge: Cambridge University Press, pp. 65–129.
D'Andrade, R. G. (1991), ‘Culturally Based Reasoning’, in A. Gellatly and D. Rogers, eds.,Cognition and Social Worlds, Oxford: Clarendon Press.
Epstein, S. L. (1990a), ‘Learning Plans for Competitive Domains’,Proceedings of the Seventh International Conference on Machine Learning, pp. 190–197.
Epstein, S. L. (1990b), ‘Learning to Control a Blackboard System for Game Playing’,Proceedings of the AAAI Workshop on Blackboard Systems.
Epstein, S. L. (1991),Learning under a Weak Theory, Department of Computer Science, Hunter College, Technical Report CS-TR 91-02.
Epstein, S. L. (1992), ‘Hard Questions about Easy Tasks — Issues from Learning to Play Games’, inComputational Learning Theory and Natural Learning Systems: Constraints and Prospects, Cambridge, MA: MIT Press. To appear.
Esfahany, K. H. (1992), in preparation.
Flax, M. G., Gelfand, J. J., Lane, S. H., and Handelman, D. A. (1990), ‘Integrating Neural Network and Tree Search Approaches to Produce an Auto-Supervised System that Learns to Play Games’, inProceedings of the 1992 International Joint Conference on Neural Networks. In press.
Goodman, N. (1973),Fact, Fiction, and Forecast, Indianapolis, IN: Bobbs-Merrill.
Hsu, G.-T. and Simmons, R. (1991), ‘Learning Footfall Evaluation for a Walking Robot’,Proceedings of the Eighth International Machine Learning Workshop, pp. 303–307.
Kirsh, D. (1991), ‘Today, the Earwig, Tomorrow Man?’,Artificial Intelligence 47, pp. 161–184.
Laird, J. E., Rosenbloom, P.S., and Newell, A. (1987), ‘SOAR: An Architecture for General Intelligence’,Artificial Intelligence 33, pp. 1–64.
Lenat, D. B. (1976), ‘AM: An Artificial Intelligence Approach to Discovery in Mathematics’, Ph.D. Thesis, Department of Computer Science, Stanford University.
Levinson, R. (1991), Personal communication.
Levinson, R. and Snyder, R. (1991), ‘Adaptive Pattern-Oriented Chess’,Proceedings of the Eighth International Machine Learning Workshop, pp. 85–89.
Lindsay, R. K., Buchanan, B. G., Feigenbaum, E. A., and Lederberg, J. (1980),Applications of Artificial Intelligence for Organic Chemistry: The Dendral Project, New York: McGraw-Hill.
Maes, P. and Brooks, R. A. (1990), ‘Learning to Coordinate Behaviors’,Proceedings of the Eighth National Conference on Artificial Intelligence, pp. 796–802.
Mahadevan, S. and Connell, J. (1991), ‘Scaling Reinforcement Learning to Robotics by Exploiting the Subsumption Architecture’,Proceedings of the Eighth International Machine Learning Workshop, pp. 328–332.
Michie, D. (1986), ‘Trial and Error’ inOn Machine Intelligence. Second edition, pp. 11–23. Chichester, England: Ellis Horwood Ltd.
Minsky, M. (1986),The Society of Mind, New York: Simon & Schuster.
Minton, S. (1988),Learning Search Control Knowledge — An Explanation-Based Approach, Boston: Kluwer Academic.
Mitchell, T., Allen, J., Chalasani, P., Cheng, J., Eitzioni, O., Ringuette, M. N., and Schlimmer, J. C. (1990), ‘Theo A Framework for Self-Improving Systems’, in K. Vanlehn, ed.,Architectures for Intelligence, Boston: Erlbaum.
Newell, A., Shaw, J. C., and Simon, H. A. (1963), ‘Empirical Explorations with the Logic Theory Machine: A Case study in Heuristics’, in E. A. Feigenbaum and J. Feldman, eds.,Computers and Thought, New York: McGraw-Hill.
Nilsson, N. J. (1980),Principles of Artificial Intelligence, Palo Alto: Tioga Publishing.
Painter, J. (1992), ‘Pattern Recognition for Decision Making in a Competitive Environment’, Master's Thesis, Department of Computer Science, Hunter College of the City University of New York. In preparation.
Pierce, D. (1991), ‘Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus’,Proceedings of the Eighth International Machine Learning Workshop, pp. 338–342.
Ring, M. (1991), ‘Incremental Development of Complex Behaviors through Automatic Construction of Sensory-Motor Hierarchies’,Proceedings of the Eighth International Machine Learning Workshop, pp. 343–347.
Sacerdoti, E. D. (1974), ‘Planning in a Hierarchy of Abstraction Spaces’,Artificial Intelligence 5, pp. 115–135.
Schank, R. and Abelson, R. (1977),Scripts, Plans, Goals, and Understanding: An Inquiry into Human Knowledge Structures, Hillsdale, NJ: Erlbaum.
Shortliffe, E. H. (1976),Computer-Based Medical Consultations: MYCIN, New York: Elsevier.
Tinbergen, N. (1951),The Study of Instinct, Oxford: Oxford University Press.
Wierzbicka, A. (1985),Lexicography and Conceptual Analysis, Ann Arbor, MI: Karoma Publishers.
Zaslavsky, C. (1982),Tic Tac Toe and Other Three-in-a-Row Games, from Ancient Egypt to the Modern Computer, Crowell.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Epstein, S.L. The role of memory and concepts in learning. Mind Mach 2, 239–265 (1992). https://doi.org/10.1007/BF02454222
Issue Date:
DOI: https://doi.org/10.1007/BF02454222