Abstract
This research examines the metaphor of goal-driven planning as a tool for performing the integration of multiple learning algorithms. In case-based reasoning systems, several learning techniques may apply to a given situation. In a failure-driven learning environment, the problems of strategy construction are to choose and order the best set of learning algorithms or strategies that recover from a processing failure and to use those strategies to modify the system's background knowledge so that the failure will not be repeated in similar future situations. A solution to this problem is to treat learning-strategy construction as a planning problem with its own set of goals. Learning goals, as opposed to ordinary goals, specify desired states in the background knowledge of the learner, rather than desired states in the external environment of the planner. But as with traditional goalbased planners, management and pursuit of these learning goals becomes a central issue in learning. Example interactions of learning-goals are presented from a multistrategy learning system called Meta-AQUA that combines a case-based approach to learning with nonlinear planning to achieve goals in a knowledge space.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aamodt, A.: Explanation-driven case-based reasoning. In S. Wess, K.-D. Althoff, and M. M. Richter (Eds.), Topics in case-based reasoning (EWCBR-93). Berlin: Springer-Verlag (1994) 274–288
Brodley, C. E.: Addressing the selective superiority problem: Automatic algorithm / model class selection. Machine Learning: Proceedings of the Tenth International Conference. San Mateo, CA: Morgan Kaufmann (1993) 17–24
Collins, G., Birnbaum, L., Krulwich, B., Freed, M.: The role of self-models in learning to plan. In A. L. Meyrowitz and S. Chipman (Eds.), Foundations of knowledge a cquisition: Machine learning. Boston: Kluwer Academic Publishers (1993) 117–143
Cox, M. T.: Introspective multistrategy learning (Cognitive Science Tech. Rep. No. 2). Atlanta: Georgia Institute of Technology, College of Computing (1993)
Cox, M. T., Ram, A.: Using introspective reasoning to select learning strategies. In R. S. Michalski and G. Tecuci (Eds.), Proceedings of the First International Workshop on Multistrategy Learning. Washington, DC: George Mason University, Center for Artificial Intelligence (1991) 217–230
Cox, M. T., Ram, A.: Multistrategy learning with introspective meta-explanations. D. Sleeman and P. Edwards (Eds.), Machine Learning: Proceedings of the Ninth International Conference. San Mateo, CA: Morgan Kaufmann (1992) 123–128
DeJong, G., Mooney, R.: Explanation-based learning: An alternative view, Machine Learning 1(2) (1986) 145–176
Fox, S., Leake, D.: Modeling case-based planning for repairing reasoning failures. In M. Cox and M. Freed (Eds.), Proceedings of the 1995 AAAI Spring Symposium on Representing Mental States and Mechanisms. Menlo Park, CA: AAAI Press (1995) 31–38
Ghosh, S., Hendler, J., Kambhampati, S., Kettler, B.: UM Nonlin [a Common Lisp implementation of A. Tate's Nonlin planner]. Maintained at the Dept. of Computer Science, University of Maryland, College Park, MD. Available by anonymous ftp from cs.umd.edu in directory /pub/nonlin (1992)
Hammond, K. J.: Learning and enforcement: Stabilizing environments to facilitate activity. B. W. Porter and R. Mooney (Eds.), Machine Learning: Proceedings of the Seventh International Conference. San Mateo, CA: Morgan Kaufmann (1990) 204–210
Hammond, K., Converse, T., Marks, M., Seifert, C.: Opportunism and learning. In J. L. Kolodner (Ed.), Case-based learning. Boston: Kluwer Academic (1993) 85–115
Hunter, L. E.: Planning to learn. Proceedings of the Twelfth Annual Conference of the Cognitive Science Society. Hillsdale, NJ: LEA (1990) 261–276
Kerner, Y.: Case-based evaluation in computer chess. In M. Keane, J.-P. Haton, and M. Manago (Eds.), Topics in case-based reasoning (EWCBR-94). Berlin: Springer-Verlag (this volume)
Kolodner, J. L.: Case-based reasoning. San Mateo, CA: Morgan Kaufmann (1993)
Leake, D.: Evaluating explanations: A content theory. Hillsdale, NJ: LEA (1992)
Lebowitz, M.: Experiments with incremental concept formation: UMIMEM. Machine Learning 2 (1987) 103–138.
Michalski, R. S.: Inferential theory of learning: Developing foundations for multistrategy learning. In R. S. Michalski and G. Tecuci (Eds.), Machine learning: A multistrategy approach IV. San Francisco: Morgan Kaufmann (1994) 3–61
Minsky, M. L.: Steps Towards Artificial Intelligence. In E. A. Feigenbaum and J. Feldman (Eds.), Computers and thought. New York: McGraw Hill (1963) 406–450
Mitchell, T., Keller, R., Kedar-Cabelli, S.: Explanation-based generalization: A unifying view, Machine Learning 1(1) (1986) 47–80
Oehlmann, R., Edwards, P., Sleeman, D.: Changing the viewpoint: Re-indexing by introspective questioning. In Proceedings of the Sixteenth Annual Conference of the Cognitive Science Society. Hillsdale, NJ: LEA (1994) 675–680
Plaza, E., Arcos, J. L.: Reflection and analogy in memory-based learning. In R. S. Michalski and G. Tecuci (Eds.), Proceedings of the Second International Workshop on Multistrategy Learning. Fairfax, VA: George Mason University, Center for Artificial Intelligence (1993) 42–49
Provost, F. J., Buchanan, B. G.: Inductive policy. Proceedings of the Tenth National Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press (1992) 255–261
Quilici, A.: Toward automatic acquisition of an advisory system's knowledge base. Applied Intelligence (to appear)
Ram, A.: A theory of questions and question asking. Journal of the Learning Sciences 1(3&4) (1991) 273–318.
Ram, A.: Indexing, elaboration and refinement: Incremental learning of explanatory cases. Machine Learning 10(3) (1993) 201–248.
Ram, A., Cox, M. T.: Introspective reasoning using meta-explanations for multistrategy learning. In R. S. Michalski and G. Tecuci (Eds.), Machine learning: A multistrategy approach IV. San Francisco: Morgan Kaufmann (1994) 349–377
Ram, A., Hunter, L.: The use of explicit goals for knowledge to guide inference and learning. Applied Intelligence, 2(1) (1992) 47–73
Ram, A., Leake, D.: Learning, goals, and learning goals. In A. Ram and D. Leake (Eds.), Goal-driven learning. Cambridge, MA: MIT Press/Bradford Books (to appear)
Redmond, M. A.: Learning by observing and understanding expert problem solving (Tech. Rep. No. GIT-CC-92/43). Doctoral dissertation, Atlanta: Georgia Tech (1992)
Schaffer, C.: Selecting a classification method by cross-validation. Machine Learning, 13(1)(1993) 135–143
Schank, R. C.: Dynamic memory: A theory of reminding and learning in computers and people. Cambridge, UK: Cambridge University Press (1982)
Schank, R. C.: Explanation patterns: Understanding mechanically and creatively.Hillsdale, NJ: LEA (1986)
Schank, R. C., Kass, A., Riesbeck, C. K.: Inside case-based explanation. Hillsdale, NJ: LEA (1994)
Stroulia, E., Goel, A.: Functional representation and reasoning for reflective systems. Applied Artificial Intelligence (to appear)
Sussman, G. J.: A computer model of skill acquisition. New York: American Elsevier (1975)
Tate, A.: Project planning using a hierarchic non-linear planner (Tech. Rep. No. 25). Edinburgh, UK: University of Edinburgh, Department of Artificial Intelligence (1976)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cox, M.T., Ram, A. (1995). Interacting learning-goals: Treating learning as a planning task. In: Haton, JP., Keane, M., Manago, M. (eds) Advances in Case-Based Reasoning. EWCBR 1994. Lecture Notes in Computer Science, vol 984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60364-6_27
Download citation
DOI: https://doi.org/10.1007/3-540-60364-6_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60364-1
Online ISBN: 978-3-540-45052-8
eBook Packages: Springer Book Archive