Abstract
The constructivist paradigm in Artificial Intelligence has been definitively inaugurated in the earlier 1990’s by Drescher’s pioneer work [10]. He faces the challenge of design an alternative model for machine learning, founded in the human cognitive developmental process described by Piaget [x]. His effort has inspired many other researchers.
In this paper we present an agent learning architecture situated on the constructivist approach. We present details about the architecture, pointing the autonomy of the agent, and defining what is the problem that it needs to solve. We focus mainly on the learning mechanism, designed to incrementally discover deterministic environmental regularities, even in non-deterministic worlds. Finally, we report some experimental results and discuss how this agent architecture can lead to the construction of more abstract concepts.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barandiaran, X. 2004. Behavioral Adaptive Autonomy: a milestone on the A Life route to AI? Proceedings of the 9th International Conference on Artificial Life. MIT Press, Boston, Massachussets, pp. 514–521.
Belpaeme, T., Steels, L., & van Looveren, J. 1998. The construction and acquisition of visual categories. In Birk, A. and Demiris, J., editors, Learning Robots, Proceedings of the EWLR-6, Lecture Notes on Artificial Intelligence 1545. Springer.
Birk, Andreas & Paul, Wolfgang. 2000. Schemas and Genetic Programming. Ritter, Cruse, Dean (Eds.), Prerational Intelligence: Adaptive Behavior and Intelligent Systems without Symbols and Logic, Volume II, Studies in Cognitive Systems 36, Kluwer.
Boden, M. 1979. Piaget. Glasgow: Fontana Paperbacks.
Booker, L. B., Goldberg, D. E. & Holland, J. H. 1989. Classifier Systems and Genetic Algorithms. Artificial Intelligence, vol. 40, p. 235–282.
Buisson J.-C. 2004. A rhythm recognition computer program to advocate interactivist perception. Cognitive Science, 28:1, p.75–87.
Crook, P. & Hayes, G. 2003. Learning in a State of Confusion: Perceptual Aliasing in Grid World Navigation. In Proceedings of Towards Intelligent Mobile Robots, UWE, Bristol.
Damasio, A. 1994. Descartes’ Error: Emotion, Reason and the Human Brain. New York: Avon Books.
DeJong, E. D. 1999. Autonomous Concept Formation. In: Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence IJCAI.
Drescher, Gary. 1991. Mide-Up Minds: A Construtivist Approach to Artificial Intelligence. MIT Press.
Holmes & Isbell. 2005. Schema Learning: Experience-based Construction of Predictive Action Models. In Advances in Neural Information Processing Systems, volume 17.
Inhelder B. & Cellerier G. 1992. Le cheminement des découvertes de l’enfant. Neuchâtel: Delachaux et Niestlé.
Kohonen, Teuvo. Self-Organization and Associative Memory. Berlin: Springer-Verlag, 1989.
LeDoux, J.E. 1996. The Emotional Brain. New York: Simon and Schuster.
Langley, P., Zytkow, J. 1989. Data-Driven Approaches to Empirical Discovery. Artif. Intell. 40(1–3): 283–312.
Mitchell, T. 1982. Generalization as search. Artificial Intelligence, 18, p.203–226.
Montangero, J., & Maurice-Naville, D. 1997. Piaget or the advance of knowledge. New York: Lawrence. Erlbaum Associates.
Morrison, C., Oates, T. & King, G. 2001. Grounding the Unobservable in the Observable: The Role and Representation of Hidden State in Concept Formation and Refinement. In Working Notes of AAAI Spring Symposium Workshop: Learning Grounded Representations.
Müller, J.-P. & Rodriguez, M. 1996. A constructivist approach to autonomous systems, Growing Mind Symposium (Piaget Centenary), Geneva.
Muñoz, Mauro H. S. 1999. Proposta de Modelo Sensório Cognitivo inspirado na Teoria de Jean Piaget. Porto Alegre: PGCC/UFRGS. (Thesis)
Perotto, F. Alvares, L. O. 2006. Learning Environment Regularities with a Constructivist Agent. Fifth International Joint Conference on Autonomous Agents and Multi Agent Systems (AAMAS 2006). Hakodate, Japan.
Piaget, Jean. 1951. Symbol Formation — Play, Dreams and Imitation in Childhood. London: Heinemann.
Piaget, Jean. 1953. The Origins of Intelligence in the Child. London: Routledge & Kegan Paul.
Piaget, Jean. 1957. Construction of Reality in the Child. London: Routledge & Kegan Paul.
Quinlan, J. 1986. Induction of Decision Trees. Machine Learning, vol. 1, p. 81–106.
Singh, S., Barto, A.G. & Chentanez, N. 2004. Intrinsically Motivated Reinforcement Learning. 18th Annual Conference on Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada.
Sloman, Aaron. 1999. Review of Affective Computing. AI Magazine 20 (1): 127–133.
Suchman, L. A. 1987. Plans and Situated Actions. Cambridge: Cambridge University Press.
Wazlawick, R. Costa, A. C. R. 1995. Non-Supervised Sensory-Motor Agents Learning. In: Artificial Neural Nets and Genetic Algorithms. New York: Springer-Verlag: 49–52.
Holland, J. Holyoak, K. Nisbett, R & Thagard, P. 1986. Induction: Processes of Inference, Learning, and Discovery. MIT Press, Cambridge.
Chaput, H. 2004. The Constructivist Learning Architecture. PhD Thesis. University of Texas.
Gennari, J. H. Langley, P. & Fisher, D. H. 1989. Models of incremental concept formation. Artificial Intelligence, 40, 11–61.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag London Limited
About this paper
Cite this paper
Perotto, F.S., Älvares, L.O. (2007). Incremental Inductive Learning in a Constructivist Agent. In: Bramer, M., Coenen, F., Tuson, A. (eds) Research and Development in Intelligent Systems XXIII. SGAI 2006. Springer, London. https://doi.org/10.1007/978-1-84628-663-6_10
Download citation
DOI: https://doi.org/10.1007/978-1-84628-663-6_10
Publisher Name: Springer, London
Print ISBN: 978-1-84628-662-9
Online ISBN: 978-1-84628-663-6
eBook Packages: Computer ScienceComputer Science (R0)