Abstract
In this paper we presented FAILSAFE-II, a system that performs adaptive search by learning on-line form its failures. The key contribution of this system is its use of the preservability of failures. Preservability assumption allows FAILSAFE-II to over-generalize the failures and discard some solutions to the problem along with the non-solutions. This leads to learning of search control rules which could not be learned by systems like PRODIGY [4], STATIC [2] or the other systems that learn from search failures. We demonstrated FAILSAFE-II's performance improvement in three domains including one in which PRODIGY failed to learn effective control rules.
This paper originally appeared in a modified form in Proceedings of the Eighth National Conference on AI, July 29–August 3, 1990, AAAI Press/MIT Press.
Preview
Unable to display preview. Download preview PDF.
References
DeJong, G. F. and Mooney, R. J. Explanation-based Learning: An Alternative view. Machine Learning 1(2) (1986) 145–176.
Etzioni, O. Why Prodigy/EBL works. In National Conference on Artificial Intelligence (1990) 916–922.
Fikes, R. E. and Nilsson, N. J. STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving. Artificial Intelligence Journal 2 (1971) 189–208.
Minton, S. Learning Effective Search Control Knowledge: An Explanation-Based Approach. Carnegie-Mellon University PhD thesis (1988).
Mitchell, T. M., Keller, R. and Kedar-Cabelli, S. Explanation-Based Generalization: A Unifying View. Machine Learning Journal 1(1) (1986) 47–80.
Mostow, D. J. and Bhatnagar, N. Failsafe—A Floorplanner that Uses EBG to Learn from Its Failures. In International Joint Conference on Artificial Intelligence (1987) 249–255.
Mostow, D. J. Machine Transformation of Advice into a Heuristic Search Procedure. In Machine Learning: An Artificial Intelligence Approach, Volume I. J. G. Carbonell, R. S. Michalski and T. M. Mitchell, editors, Tioga Publishing Company (1983).
Stallman, R. and Sussman, G. Forward Reasoning and Dependency Directed Backtracking in a System for Computer-aided Circuit Analysis. Artificial Intelligence Journal 9 (1977) 135–196.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Bhatnagar, N. (1993). Adaptive search by learning from incomplete explanations of failures. In: Hanson, S.J., Remmele, W., Rivest, R.L. (eds) Machine Learning: From Theory to Applications. Lecture Notes in Computer Science, vol 661. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56483-7_24
Download citation
DOI: https://doi.org/10.1007/3-540-56483-7_24
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56483-6
Online ISBN: 978-3-540-47568-2
eBook Packages: Springer Book Archive