Abstract
Easy missions is an approach to machine learning that seeks to synthesize solutions for complex tasks from those for simpler ones. ISLES (Incrementally Staged Learning from Easier Subtasks) [1] is a genetic programming (GP) technique that achieves this by using identified goals and fitness functions for subproblems of the overall problem. Solutions evolved for these subproblems are then reused to speed up learning, either as automatically defined functions (ADF) or by seeding a new GP population. Previous positive results using both approaches for learning in multi-agent systems (MAS) showed that incremental reuse using easy missions achieves comparable or better overall fitness than single-layered GP. A key unresolved issue dealt with hybrid reuse using ADF with easy missions. Results in the keep-away soccer (KAS) [2] domain (a test bed for MAS learning) were also inconclusive on whether compactness-inducing reuse helped or hurt overall agent performance. In this paper, we compare reuse using single-layered (with and without ADF) GP and easy missions GPs to two new types of GP learning systems with incremental reuse.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hsu, W.H., Gustafson, S.M.: Genetic programming and multi-agent layered learning by reinforcements. In: GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, New York, pp. 764–771. Morgan Kaufmann Publishers, San Francisco (2002)
McAllester, D., Stone, P.: Keeping the ball from CMUnited-99. In: Stone, P., Balch, T., Kraetzschmar, G.K. (eds.) RoboCup 2000. LNCS (LNAI), vol. 2019, p. 333. Springer, Heidelberg (2001)
Luke, S.: Issues in Scaling Genetic Programming: Breeding Strategies, Tree Generation, and Code Bloat. PhD thesis, Department of Computer Science, University of Maryland, A. V. Williams Building, University of Maryland, College Park, MD 20742 USA (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Harmon, S., Rodríguez, E., Zhong, C., Hsu, W. (2004). A Comparison of Hybrid Incremental Reuse Strategies for Reinforcement Learning in Genetic Programming. In: Deb, K. (eds) Genetic and Evolutionary Computation – GECCO 2004. GECCO 2004. Lecture Notes in Computer Science, vol 3103. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24855-2_79
Download citation
DOI: https://doi.org/10.1007/978-3-540-24855-2_79
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22343-6
Online ISBN: 978-3-540-24855-2
eBook Packages: Springer Book Archive