Abstract
We study the problems of efficiently learning infinite branches for finite state trees and winninig strategies for closed finite-state games using membership, and branch or strategy queries, respectively. We show that generally no efficient branch learning algorithm exists but we provide such algorithms for several natural cases, in particular for deadend free finite-state trees, the class of trees such that the set of infinite branches has positive measure, and several classes of modulo trees. Furthermore, we find a way to apply Angluin's results about the identification of deterministic finite automata from queries, which yields positive and negative strategy learning results, in particular, we show that the class of deadend free closed finite-state games is efficiently strategy learnable from membership and strategy queries.
Supported by the Deutsche Forschungsgemeinschaft (DFG) Graduiertenkolleg “Beherrschbarkeit komplexer Systeme” (GRK 209/2-96).
Supported by the Deutsche Forschungsgemeinschaft (DFG) grant Am 60/9-1.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin. A note on the number of queries needed to identify regular languages. Information and Control, 51(1):76–87, 1981.
D. Angluin. Learning regular sets from queries and counterexamples. Inform. Comput., 75(2):87–106, Nov. 1987.
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
D. Angluin. Negative results for equivalence queries. Machine Learning, 5(2):121–150, June 1990.
J. R. Büchi and L. H. Landweber. Solving sequential conditions by finite-state strategies. Transactions of the American Mathematical Society, 138:295–311, 1969.
J. Case, M. Ott, A. Sharma, and F. Stephan. Learning to win process-control games watching game-masters. Submitted.
P. R. Halmos. Measure Theory. Van Nostrand, Princeton, New Jersey, 1950.
L. P. Kaelbling. Learning in Embedded Systems. The MIT Press: Cambridge, MA, 1993.
M. Kummer and M. Ott. Effective strategies for enumeration games. In H. K. Büning, editor, Proceedings of Computer Science Logic CSL '95, volume 1092 of LNCS, pages 368–387, Berlin, 1996. Springer.
M. Kummer and M. Ott. Learning branches and learning to win closed games. In Proceedings of Ninth Annual Conference on Computational Learning Theory, pages 280–291, New York, 1996. ACM.
H. Lescow. On polynomial-size programs winning finite-state games. In CAV: International Conference on Computer Aided Verification, pages 239–252, 1995.
R. McNaughton. Infinite games played on finite graphs. Annals of Pure and Applied Logic, 65:149–184, 1993.
M. Ott and F. Stephan. Structural measures for games and process control in the branch learning model. In S. Ben-David, editor, Proceedings of the Third European Conference on Computational Learning Theory, volume 1208 of LNAI, pages 94–108. Springer, 1997.
C. D. Rosin and R. K. Belew. A competitive approach to game learning. In Proceedings of the 9th Annual ACM Conference on Computational Learning Theory (COLT'96), pages 292–302. ACM Press, New York, NY, 1996.
W. Thomas. On the synthesis of strategies in infinite games. In STACS 95, volume 900 of LNCS, pages 1–13. Springer-Verlag, 1995.
R. Wiehagen. From inductive inference to algorithmic learning theory. New Generation Computing, 12, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ott, M., Stephan, F. (1997). The complexity of learning branches and strategies from queries. In: Leong, H.W., Imai, H., Jain, S. (eds) Algorithms and Computation. ISAAC 1997. Lecture Notes in Computer Science, vol 1350. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63890-3_31
Download citation
DOI: https://doi.org/10.1007/3-540-63890-3_31
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63890-2
Online ISBN: 978-3-540-69662-9
eBook Packages: Springer Book Archive