Abstract
In order to scale to problems with large or continuous state-spaces, reinforcement learning algorithms need to use function approximation. Neural networks are one commonly used approach, with most work so far using fixed-architecture networks. Previous supervised learning research has shown that constructive networks which grow their architecture during training outperform fixed-architecture networks. This paper extends the sarsa algorithm to use a cascade constructive network, and shows it outperforms a fixed-architecture network on two benchmark tasks.
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.
References
Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning 3, 9–44 (1988)
Lin, L.: Reinforcement Learning for Robots Using Neural Networks, PhD thesis, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA (1993)
Rummery, G., Niranjan, M.: On-line Q-Learning Using Connectionist Systems. Cambridge University Engineering Department, Cambridge (1994)
Crites, R.H., Barto, A.G.: Improving Elevator Performance Using Reinforcement Learning. In: NIPS-8 (1996)
Tesauro, G.J.: Temporal difference learning and TD-Gammon. Communications of the ACM 38(3), 58–68 (1995)
Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing II, pp. 524–532. Morgan Kauffman, San Francisco (1990)
Waugh, S.G.: Extending and benchmarking Cascade-Correlation, PhD thesis, Department of Computer Science, University of Tasmania (1995)
Thrun, S., Schwartz, A.: Issues in Using Function Approximation for Reinforcement Learning. In: Proceedings of the Fourth Connectionist Models Summer School, Hillsdale, NJ (December 1993)
Rivest, F., Precup, D.: Combining TD-learning with Cascade-correlation Networks. In: Twentieth International Conference on Machine Learning, Washington DC (2003)
Bellemare, M.G., Precup, D., Rivest, F.: Reinforcement Learning Using Cascade-Correlation Neural Networks, Technical Report RL-3.04, McGill University, Canada (2004)
Prechelt, L.: Investigation of the CasCor Family of Learning Algorithms. Neural Networks 10(5), 885–896 (1997)
Adams, A., Waugh, S.: Function Evaluation and the Cascade-Correlation Architecture. In: Proceedings of the1995 IEEE International Conference on Neural Networks, pp. 942–946 (1995)
Lahnajarvi, J.J.T., Lehtokangas, M.I., Saarinen, J.P.P.: Evaluation of constructive neural networks with cascaded architectures. Neurocomputing 48, 573–607 (2002)
Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: Safely approximating the value function. In: NIPS-7 (1995)
Sutton, R.S.: Generalisation in reinforcement learning: Successful examples using sparse coarse coding. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference, pp. 1038–1044. The MIT Press, Cambridge (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vamplew, P., Ollington, R. (2005). On-Line Reinforcement Learning Using Cascade Constructive Neural Networks. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553939_80
Download citation
DOI: https://doi.org/10.1007/11553939_80
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28896-1
Online ISBN: 978-3-540-31990-0
eBook Packages: Computer ScienceComputer Science (R0)