The Role of the Critic in Learning Systems
Buchanan, Mitchell, Smith, and Johnson (1978) described a general model of learning systems that included a component called the Critic. The task of the Critic was described as threefold: evaluation of the past actions of the performance element of the learning system, localization of credit and blame to particular portions of that performance element, and recommendation of possible improvements and modifications in the performance element. This article analyzes these three tasks in detail and surveys the methods that have been employed in existing learning systems to accomplish them. The principle method used to evaluate the performance element is to develop a global performance standard by (a) consulting an external source of knowledge, (b) consulting an internal source of knowledge, or (c) conducting deep search. Credit and blame have been localized by (a) asking an external knowledge source to do the localization, (b) factoring the global performance standard to produce a local performance standard, and (c) conducting controlled experiments on the performance element. Recommendations have been conmiunicated to the learning element using (a) local training instances, (b) correlation coefficients, and (c) partially-instantiated schemata.
KeywordsPerformance Standard Learning System Production Rule Knowledge Source Axiom System
Unable to display preview. Download preview PDF.
- Bennett, J. S. and Hollander, C. R., 1981, DART: An expert system for computer fault diagnosis. Proceedings of IJCAI-81, Vancouver, Canada.Google Scholar
- Buchanan, B. G., Mitchell, T. M., Smith, R. G., and Johnson, C. R. Jr., 1978, Models of learning systems, in: “Encyclopedia of Computer Science and Technology.”Google Scholar
- Buchanan, B. G. and Mitchell, T. M., 1978, Model-directed learning of production rules, in: “Pattern-Directed Inference Systems,” Waterman, D. A. and Hayes-Roth F., eds., Academic Press, New York.Google Scholar
- Davis, R., 1976, “Applications of meta-level knowledge to the construction, maintenance, and use of large knowledge bases,” Rep. No. STAN CS-76–552, Stanford University, Stanford, California.Google Scholar
- Michalski, R. S., 1978, “Pattern recognition as knowledge-guided induction,” Rep. No. 927, Department of Computer Science, University of Illinois at Urbana-Champaign.Google Scholar
- Minsky, M., 1963, Steps toward artificial intelligence, “Computers and Thought,” Feigenbaum, K. and Feldman, J., eds., McGraw-Hill, New York.Google Scholar
- Mitchell, T. M., 1978, “Version Spaces: An approach to concept learning,” Rep. No. STAN-CS-78–711, Stanford University, Stanford, California.Google Scholar
- Mitchell, T. M., Utgoff, P. E., Nudel, B., and Banerji, R. B., 1981, Learning problem-solving heuristics through practice. Proceedings of IJCAI-81, Vancouver, Canada.Google Scholar
- Samual, A. L., 1963, Some studies in machine learning using the game of checkers, in: “Computers and Thought,” Feigenbaum, E. A. and Feldman, J., eds., McGraw-Hill, New York.Google Scholar
- Shortliffe, E. G., 1976, “Computer Based Medical Consultations: MYCIN,” American Elsevier, New York.Google Scholar
- Sussman, G. J., 1975, “A Computer Model of Skill Acquisition,” American Elsevier, New York.Google Scholar
- Winston, P. H., 1970, “Learning structural descriptions from examples,” Rep. No. MIT AI-TR-231, MIT, Cambridge, Massachusetts.Google Scholar