Abstract
In this paper we introduce a new approach to genetic programming with memory in reinforcement learning situations, which selects memories in order to increase the probability of modelling the most relevant parts of memory space. We evolve maps directly from state to action, rather than maps that predict reward based on state and action, which reduces the complexity of the evolved mappings. The work is motivated by applications to the control of autonomous robots. Preliminary results in software simulations indicate an enhanced learning speed and quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
W. Banzhaf, P. Nordin, R. E. Keller, F. D. Francone: Genetic Programming-An Introduction. Morgan Kaufmann, San Francisco, CA, (1998).
I. Harvey, P. Husbands, D. Cliff: Issues in Evolutionary Robotics. School of Cognitive and Computing Sciences, The University of Sussex, England, U.K, (1992).
N. Jakobi, P. Husbands and I. Harvey: Noise and the Reality Gap: The use of Simulation in Evolutionary Robotics In Advances in Artificial Life: Proc. 3rd European Conference on Artificial Life, Moran, F., Moreno, A., Merelo, J., Chacon, P. (eds.) Springer-Verlag, Lecture Notes in Artificial Intelligence 929 (1995) pp. 704–720.
P. R. Merlyn: Toward a Humanoid Robot: Artificial Intelligence and the Confluence of Technologies. SRI Consulting, http://future.sri.com/ BIP/datalog/dldesc/2031.html, (1996).
P. Nordin: Evolutionary Program Induction of binary Machine Code and its Application. Krehl Verlag, Mnster, Germany.
P. Nordin, W. Banzhaf, M. Brameier: Evolution of a world model for a miniature robot using genetic programming. Robotics and Autonomous Systems, Elsevier Science B.V. 25, (1998), pp 105–116.
M. Salganicoff: Tolerating Concept and Sampling in Lazy Learning Using Prediction Error Context Switching. In Artificial Intelligence Review 1, 1Kluwer Academic Publishers, Netherlands. (1997), p. 133–155.
S. Sutton, A.G. Barto: Reinforcement Learning-An Introduction. MIT Press, Cambridge MA, (1998).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Andersson, B., Svensson, P., Nordin, P., Nordahl, M. (1999). Reactive and Memory-Based Genetic Programming for Robot Control. In: Poli, R., Nordin, P., Langdon, W.B., Fogarty, T.C. (eds) Genetic Programming. EuroGP 1999. Lecture Notes in Computer Science, vol 1598. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48885-5_13
Download citation
DOI: https://doi.org/10.1007/3-540-48885-5_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65899-3
Online ISBN: 978-3-540-48885-9
eBook Packages: Springer Book Archive