Abstract
We propose a method for selecting the characteristic region in the environment based on the occurrence probability of the pattern. If the occurrence probability of the pattern is unknown in initial stage, estimation of the distribution of the pattern and selection of the characteristic region must be done simultaneously. We noticed that a method for exploration of the state-space in reinforcement learning was similar to such task. Then, we propose a method for selecting the characteristic region by repeating observation and action in the environment. In the observation using only one resolution, the position in the environment can not be decided. The multi-resolution concept is introduced in order to solve this problem. The experimental result shows that the characteristic region is selected from the environment.
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
L. P. Kaelbling, M. L. Littman, Andrew W. Moore: Reinforcement Learning: A Survey; Journal of Artificial Intelligence Research 4, pp.237–285 (1996).
K. Miyazaki, M. Yamamura and S. Kobayashi: k-Certainty Exploration Method: An Action Selector on Reinforcement Learning to Identify the Environment; Journal of Artificial Intelligence, Vol.91, pp.155–171 (1997).
K. Miyazaki, M. Yamamura and S. Kobayashi: 1-Certainty Exploration Method: An Action Selector to Identify the Identify the Environment-An Extension of k-Certainty Exploration Method to Stochastic MDPs-; Journal of Japanese Society for Artificial Intelligence, Vol.11, pp.804–808 (1996).
K. Miyazaki, M. Yamamura and S. Kobayashi: MarcoPolo-A Reinforcement Learning System Considering Tradeoff Exploration and Exploitation under Markovian Environment; Proc. of 4th Int. Conf. on Soft Computing, pp.561–564 (1996).
Bandera, C., Vico, F. J., Bravo, J. M., Harmon, M. E., and Baird, L. C: Residual Q-learning applied to visual attention; Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy, 3–6 July, pp. 20–27. (1996).
Moddeling Saccadic Targeting in Visual Search; R. P. N. Rao, G. J. Zelinsky, M. M. Hayhoe, D. H. Ballard.: Advances in Neural Information Processing Systems 8, D. S. Touretzky, M. C. Mozer, M. E. Hasselmo, eds., MIT Press (1996).
B. Takacs, H. Wechsler: A Dynamic and Multiresolution Model of Visual Attention and Its Application to Facial Landmark Detection; Computer Vision and Image Understanding Vol.70, pp.63–73 (1998).
I. Marsic: Data-Driven Shifts of Attention in Wavelet Scale Space; CAIP-TR-166, CAIP Center, Rutgers University, September (1993).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matsui, T., Matsuo, H., Iwata, A. (2000). A Region Selecting Method Which Performs Observation and Action in the Multi-resolution Environment. In: Mizoguchi, R., Slaney, J. (eds) PRICAI 2000 Topics in Artificial Intelligence. PRICAI 2000. Lecture Notes in Computer Science(), vol 1886. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44533-1_17
Download citation
DOI: https://doi.org/10.1007/3-540-44533-1_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67925-7
Online ISBN: 978-3-540-44533-3
eBook Packages: Springer Book Archive