Abstract
In many real-world settings, particularly economic settings, an adaptive agent is interested in maximizing its cumulative reward. This may require a choice between different problems to learn, where the agent must trade optimal reward against learning difficulty. A landscape is one way of representing a learning problem, where highly rugged landscapes represent difficult problems. However, ruggedness is not directly measurable. Instead, a proxy is needed.
We compare the usefulness of three different metrics for estimating ruggedness on learning problems in an information economy domain. We empirically evaluate the ability of each metric to predict ruggedness and use these metrics to explain past results showing that problems that yield equal reward when completely learned yield different profits to an adaptive learning agent.
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
Christopher H. Brooks, Robert S. Gazalle, Rajarshi Das, Jeffrey O. Kephart, Jeffrey K. MacKie-Mason, and Edmund H. Durfee. Model selection in an information economy: Choosing what to learn. Computational Intelligence, 2002. to appear.
Josselin Garnier and Leila Kallel. How to detect all attraction basins of a function. In Theoretical Aspects of Evolutionary Computation, pages 343–365. Springer-Verlag, 2000.
Wim Hordjik. A measure of landscapes. Evolutionary Computation, 4(4):336–366, 1996.
Terry Jones. Evolutionary Algorithms, Fitness Landscapes, and Search. PhD thesis, University of New Mexico, May 1995.
Terry Jones and Stephanie Forrest. Fitness distance correlation as a measure of problem difficulty for genetic algorithms. In Larry Eshelman, editor, Proceedings of the Sixth International Conference on Genetic Algorithms, pages 184–192, San Francisco, 1995. Morgan Kauffman.
L. Kallel, B. Naudts, and C.R. Reeves. Properties of fitness functions and search landscapes. In L. Kallel, B. Naudts, and A. Rogers, editors, Theoretical Aspects of Evolutionary Computation, pages 175–206. Springer-Verlag, 2000.
Stuart Kauffman. Origins of Order: Self-organization and Selection in Evolution. Oxford University Press, New York, 1993.
William H. Press et al. Numerical Recipes. Cambridge University Press, 1992.
Sebastian Thrun. The role of exploration in learning control. In Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Systems. Van Nostrand Reinhold, Florence, Kentucky, 1992.
E. Weinberger. Correlated and uncorrelated fitness landscapes and how to tell the difference. Biological Cybernetics, 63:325–336, 1990.
Sewall Wright. The roles of mutation, inbreeding, crossbreeding and selection in evolution. In Proceedings of the 6th Congress on Genetics, page 356, 1932.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Brooks, C.H., Durfee, E.H. (2003). Using Landscape Theory to Measure Learning Difficulty for Adaptive Agents. In: Alonso, E., Kudenko, D., Kazakov, D. (eds) Adaptive Agents and Multi-Agent Systems. AAMAS AAMAS 2002 2001. Lecture Notes in Computer Science(), vol 2636. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44826-8_17
Download citation
DOI: https://doi.org/10.1007/3-540-44826-8_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40068-4
Online ISBN: 978-3-540-44826-6
eBook Packages: Springer Book Archive