Combining statistical and reinforcement learning in rule-based classification
- 407 Downloads
BYPASS is a rule-based learning algorithm designed loosely after John Holland’s Classifier System (CS) idea. In essence, CSs are incremental data processors that attempt to (self-)organize a population of rules under the guidance of certain reinforcement policy. BYPASS uses a reinforcement scheme based on predictive scoring and handles conditions similar to those in standard classification trees. However, these conditions are allowed to overlap; this makes it possible to base individual predictions on several rules (just like in committees of trees). Moreover, conditions are supplied with simple bayesian predictive distributions that evolve as data are processed. The paper presents the details of the algorithm and discusses empirical results suggesting that statistical and reinforcement-based learning blend together in interesting and useful ways.
KeywordsEvolutionary Computation Probabilistic Prediction Self-Organization Bayesian Learning Regularity Detection
Support by CICYT grants HID98-0379-C02-01 and TIC98-0272-C02-01 is appreciated.
- Butz, M. V., Goldberg, D. E., and Stolzmann, W. (2000). The Anticipatory Classifier System and Genetic Generalization. Technical Report 2000032, Illinois Genetic Algorithms Laboratory, University of Illinois at Urbana-Champaign.Google Scholar
- De Jong, K. A., Spears, W. M. and Gordon, D. F. (1993). Using Genetic Algorithms for Concept Learning. Machine Learning 13, 161–188.Google Scholar
- Denison, D. G. T., Adams, N. M., Holmes, C. C. and Hand, D. J. (2000). Bayesian Partition Modelling. Preprint available at http://stats.ma.ic.ac.uk/~dgtd/tech.html
- Freitas, A. A. (Ed.) (1999). Data Mining with Evolutionary Algorithms: Research Directions. Proceedings of the AAAI-99 & GECCO-99 Workshop on Data Mining with Evolutionary Algorithms. Technical Report WS-99-06. A.A.A.I. Press.Google Scholar
- Frey, P. W. and Slate, D. J. (1991). Letter Recognition Using Holland-style Adaptive Classifiers. Machine Learning 6, 161–182.Google Scholar
- Holland, J. H., Holyoak, K. J., Nisbett, R. E. and Thagard, P. R. (1986). Induction: Processes of Inference, Learning and Discovery. Cambridge, MA: M.I.T. Press.Google Scholar
- Muruzábal, J. (1995). Fuzzy and Probabilistic Reasoning in Simple Learning Classifier Systems. In Proceedings of the 2nd IEEE International Conference on Evolutionary Computation (Ed. D. B. Fogel), 262–266. Piscataway, NJ: I.E.E.E. Press.Google Scholar
- Muruzábal, J. (1999). Mining the Space of Generality with Uncertainty-Concerned, Cooperative Classifiers. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO-99 (Eds. W. Banzhaf, J. Daida, A. E. Eiben, M. H. Garzon, V. Honavar, M. Jakiela and R. E. Smith), 449–457. San Francisco, CA: Morgan Kaufmann.Google Scholar
- Muruzábal, J. and Muñoz, A. (1994). Diffuse Pattern Learning with Fuzzy ARTMAP and PASS. Springer-Verlag Lecture Notes in Computer Science, Vol. 866, 376–385.Google Scholar
- Tukey, J. W. (1985). Discussion of G. J. Hahn’s “More Intelligent Statistical Software and Statistical Expert Systems: Future Directions”. The American Statistician, Vol. 39.Google Scholar
- Wilson, S. W. (1987). Classifier Systems and the Animat Problem. Machine Learning 2, 199–228.Google Scholar