Abstract
Machine Learning is a rapidly growing subfield of Artificial Intelligence, and a large variety of learning algorithms have been reported in the literature. However, no one algorithm provides a totally satisfactory solution to a wide range of problems.
This chapter describes our domain-independent Integrated Learning System (ILS), and one application, which learns how to control a telecommunications network. Our approach includes a framework for combining various learning paradigms, integrating different reasoning techniques, and coordinating distributed cooperating problem-solvers.
The current implementation has five learning paradigms (agents) that cooperate to improve problem-solving performance. ILS also includes a central controller, called The Learning Coordinator (TLC), which manages control flow and communication between the agents. The agents provide TLC with advice. TLC chooses which suggestion to adopt and performs the appropriate actions. At intervals, the agents can inspect the results of the TLC’s actions and use this feedback to learn, improving the value of their future advice.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
L.A. Birnbaum and G.C. Collins, editors. Proceedings of the 8th International Machine Learning Workshop. Morgan Kaufmann, 1991.
J. Blythe and T.M. Mitchell. On becoming reactive. In A. Segre, editor, Proceedings of the 6th International Machine Learning Workshop, pages 255–257. Morgan Kaufmann, 1989.
R. Chipalkatti, S. Kheradpir, and W. Stinson. NEMACS: The NEtwork MAn-agement and Control Simulator. Technical Memorandum TM 0299-08-90-465-01, GTE Laboratories Incorporated, August 1990.
T.H. Cormen, C.E. Leiserson, and R.L. Rivest. Introduction to Algorithms. MIT Press, 1990.
G. DeJong and R. Mooney. Explanation-based learning: An alternative view. Machine Learning, 1(2):145–176, 1986.
T.G. Dietterich, R. London, K. Clarkson, and G. Dromey. Learning and inductive inference. In P.R. Cohen and E.A. Feigenbaum, editors, The Handbook of Artificial Intelligence, Volume 3, chapter XIV. Pitman Books Ltd, 1982.
S.E. Dusseault. DYNA in ILS: An overview. Technical Correspondence TC-0179-03-92-506, Computer and Intelligent Systems Laboratory, GTE Laboratories Incorporated, 1992.
T.E. Fawcett and P.E. Utgoff. Automatic feature generation for problem solving systems. In D. Sleeman and P. Edwards, editors, Proceedings of the 9th International Machine Learning Workshop, pages 144–153, 1992.
W.J. Frawley. Using functions to encode domain and contextual knowledge in statistical induction. In G. Piatetsky-Shapiro and W.J. Frawley, editors, Knowledge Discovery in Databases. AAAI Press, 1991.
W.J. Frawley, T.E. Fawcett, and K. Bradford. NETSIM: An object-oriented simulation of the operation and control of a circuit-switched network. Technical Report TN 88-506.1, Computer and Intelligent Systems Laboratory, GTE Laboratories Incorporated, 1988.
G. Iba. The application of heuristic search and discovery of macro-operators to network traffic control. Technical Memorandum TM-0062-10-88-506, Computer and Intelligent Systems Laboratory, GTE Laboratories Incorporated, 1988.
G. Iba. A heuristic approach to the discovery of macro-operators. Machine Learning, 3(4):285–317, 1989.
L. Kopeikina, R. Brandau, and A. Lemmon. Case based reasoning for continous control. In J Kolodner, editor, Proceedings of a Workshop on Case-Based Reasoning, pages 250–259. Morgan Kaufmann, 1988.
P. Kosieniak, V. Mathis, M. St Jaques, and D. Stevens. The Network Control Assistant (NCA), a real-time prototype expert system for network management. In Proceedings of First International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, pages 367–377. Association for Computing Machinery, 1988.
J.E. Laird, A. Newell, and P.S. Rosenbloom. Soar: An architecture for general intelligence. Artificial Intelligence, 33(1):1–64, 1987.
R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, editors. Machine Learning: An Artificial Intelligence Approach Vol 1. Tioga Press, 1983.
R.S. Michalski, J.G. Carbonell, and T.M. Mitchell, editors. Machine Learning: An Artificial Intelligence Approach Vol 2. Morgan Kaufmann, 1986.
T.M. Mitchell, R.M. Keller, and S.T. Kedar-Cabelli. Explanation-based generalization: A unifying view. Machine Learning, 1(1):47–80, 1986.
N.J. Nilsson. Principles of Artificial Intelligence. Tioga Pub. Co., Palo Alto, California, 1980.
B. Porter and R. Mooney, editors. Proceedings of the 1th International Machine Learning Conference. Morgan Kaufmann, 1990.
J.R. Quinlan. Induction of decision trees. Machine Learning, 1(1):81–106, 1986.
A. Segre, editor. Proceedings of the 6th International Machine Learning Workshop. Morgan Kaufmann, 1989.
B. Silver. Meta-Level Inference. Number 1 in Studies in Computer Science and Artificial Intelligence. North Holland, 1986.
B. Silver. A hybrid approach in an imperfect domain. In G. DeJong, editor, Proceedings of AAAI Symposium on Explanation-Based Learning. American Association for Artificial Intelligence, 1988.
B. Silver. NetMan: A learning network traffic controller. In M. Matthews, editor, Proceedings of Third International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, pages 923–931. Association for Computing Machinery, 1990.
B. Silver, W. Frawley, G. Iba, and J. Vittal. An architecture for self-improving distributed heterogeneous agents. In J. Bezdek, editor, Proceedings of Fourth International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems. Association for Computing Machinery, 1991.
R.S. Sutton. Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In B. Porter and R. Mooney, editors, Proceedings of the 7th International Machine Learning Conference, pages 216–224. Morgan Kaufmann, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Silver, B. et al. (1993). A Framework for Integrating Heterogeneous Learning Agents. In: David, JM., Krivine, JP., Simmons, R. (eds) Second Generation Expert Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-77927-5_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-77927-5_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-77929-9
Online ISBN: 978-3-642-77927-5
eBook Packages: Springer Book Archive