Abstract
In this paper we survey research being conducted on multi-agent learning. The work entails both theoretical studies (with Mahendran Velauthapillai and Bala Kalyanasundaram) and empirical studies (with John Grefenstette). The main goal of both of these efforts is an understanding of the nature of the cooperation required by teams of learners for successful learning. Along the way we have observed some very interesting phenomena.
Preview
Unable to display preview. Download preview PDF.
References
R. Daley, and B. Kalyanasundaram, Probabilistic and Pluralistic Learners with Mind Changes, Proceedings Mathematical Foundaltions of Computer Science, 1992, to appear.
R. Daley, B. Kalyanasundaram, and M. Velauthapillai, The Power of Probabilism in Popperian FINite Learning, Proceedings Analogical and Inductive Inference, 1992, to appear.
R. Daley, B. Kalyanasundaram, and M. Velauthapillai, Breaking the Probability 1/2 Barrier in FIN-Type Learning, Proceedings 1992 Workshop on Computational Learning Theory, to appear.
R. Daley, L. Pitt, M. Velauthapillai, and T. Will, Relations between probabilistic and team one-shot learners, Proceedings 1991 Workshop on Computational Learning Theory, 228–239.
R.V. Freivalds, Finite Identification of General Recursive Functions by Probabilistic Strategies, Proceedings International Conference on Fundamentals of Computation Theory — FCT'79, L. Budach (ed.), 138–145, Akademie-Verlag.
E. M. Gold, Language identification in the limit, Information and Control, 10:447–474, 1967.
J. J. Grefenstette, Lamarckian learning in multi-agent environments, Proceedings 1991 Conference on Genetic Algorithms, 303–310.
J. J. Grefenstette, and C. L. Ramsey, and A. C. Schultz, Learning sequential decision rules using simulation models and competition, Machine Learning, 5(4):355–381, 1990.
S. Jain, and A. Sharma, Finite learning by a team, Proceedings 1990 Workshop on Computational Learning Theory, 163–177.
L. Pitt, Probabilistic inductive inference, J. ACM, 36(2):383–433, 1989.
L. Pitt, and C. Smith, Probability and plurality for aggregations of learning machines, Information and Computation, 77(1):77–92, 1988.
C. H. Smith, The power of pluralism for automatic program synthesis, J. ACM, 29:1144–1165, 1982.
M. Velauthapillai, Inductive inference with a bounded number of mind changes, Proceedings 1989 Workshop on Computational Learning Theory, 200–213.
R. Wiehagen, Characterization problems in the theory of inductive inference, In Automata, Languages, and Programming 1978, Lecture Notes in Computer Science 62 (Springer, Berlin, 1978), 494–508.
R. Wiehagen, R. Freivalds, and E. Kinber, On the power of probabilistic strategies in inductive inference, Theoretical Computer Science, 111–133, 1984.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Daley, R. (1993). Multi-agent learning: Theoretical and empirical studies. In: Brewka, G., Jantke, K.P., Schmitt, P.H. (eds) Nonmonotonic and Inductive Logic. NIL 1991. Lecture Notes in Computer Science, vol 659. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0030393
Download citation
DOI: https://doi.org/10.1007/BFb0030393
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56433-1
Online ISBN: 978-3-540-47557-6
eBook Packages: Springer Book Archive