Abstract
This paper presents an improvement of a recurrent learning system called LSTM-CSVM (introduced in [1]) for robot navigation applications, this approach is used to deal with some of the main issues addressed in the research area: the problem of navigation on large domains, partial observability, limited number of learning experiences and slow learning of optimal policies. The advantages of this new version of LSTM-CSVM system, are that it can find optimal paths through mazes and it reduces the number of generations to evolve the system to find the optimal navigation policy, therefore either the training time of the system is reduced. This is done by adding an heuristic methodoly to find the optimal path from start state to the goal state.can contain information about the whole environment or just partial information about it.
Chapter PDF
Similar content being viewed by others
References
Bayro-Corrochano, E., Arana-Daniel, N., Vallejo-Gutierrez, R.: Recurrent Clifford Support Machines. In: Proceedings IEEE World Congress on Computational Intelligence, Hong-Kong (2008)
Schmidhuber, J., Gagliolo, M., Wierstra, D., Gomez, F.: Recurrent Support Vector Machines, Technical Report, no. IDSIA 19-05 (2005)
Bayro-Corrochano, E., Arana-Daniel, N., Vallejo-Gutierrez, R.: Geometric Preprocessing, geometric feedforward neural networks and Clifford support vector machines for visual learning. Journal Neurocomputing 67, 54–105 (2005)
Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient ow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F. (eds.) A field guide to dynamical recurrent neural networks. IEEE Press, Los Alamitos (2001)
Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory, Technical Report FKI-207-95 (1996)
Hestenes, D., Li, H., Rockwood, A.: New algebraic tools for classical geometry. In: Sommer, G. (ed.) Geometric Computing with Clifford Algebras. Springer, Heidelberg (2001)
Gómez, F.J., Miikkulainen, R.: Active guidance for a finless rocket using neuroevolution. In: Proc. GECCO, pp. 2084–2095 (2003)
Millán, J.R., Torras, C.: A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments. J. Mach. Learn. 8, 363–395 (1992)
Sutton, R.S.: Temporal credit assignment in reinforcement learning. Ph.D. Thesis, Dept. of Computer and Information Science, University of Massachusetts, Amherst (1984)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arana-Daniel, N., López-Franco, C., Bayro-Corrochano, E. (2009). Improving Recurrent CSVM Performance for Robot Navigation on Discrete Labyrinths. In: Bayro-Corrochano, E., Eklundh, JO. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2009. Lecture Notes in Computer Science, vol 5856. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10268-4_98
Download citation
DOI: https://doi.org/10.1007/978-3-642-10268-4_98
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10267-7
Online ISBN: 978-3-642-10268-4
eBook Packages: Computer ScienceComputer Science (R0)