Abstract
This paper proposes a learning method which can discover the subgoals on the different state subspaces. It uses the improved fuzzy c-means clustering algorithm to classify the state spaces firstly, and then uses the unique direction value to find the set of subgoals, and finally creates the set of options. The experimental result shows that it can discover the subgoals automatically and quickly. This method can be adapted to the learning tasks under the dynamic audio-visual 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.
Similar content being viewed by others
References
Shi, C., Shi, Z., Wang, M.: Online Hierarchical Reinforcement Learning Based on Path-matching. Journal of Computer Research and Development 45(9), 1470–1476 (2008)
Martin, S., Doina, P.: Learning Options in Reinforcement Learning. In: Proceedings of the 5th International Symposium on Abstraction. Reformulation and Approximation, Kananaskis, Alberta, Canada, pp. 212–223 (2002)
McGovern, A., Barto, A.G.: Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density. In: Proceedings of the 18th International Conference on Machine Learning (ICML 2001), pp. 361–368 (2001)
Goel, S., Huber, M.: Subgoal Discovery for Hierarchical Reinforcement Learning Using Learned Policies. In: Proceedings of the 16th International FLAIRS Conference (FLAIRS 2003), pp. 346–350 (2003)
Wang, B., Gao, Y., Chen, Z., Xie, J., Chen, S.: K-Cluster Subgoal Discovery Algorithm for Option. Journal of Computer Research and Development 855, 851–855 (2006)
Menache, I., Mannor, S., Shimkin, N.: Q-cut - dynamic discovery of sub-goals in reinforcement learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol. 2430, p. 295. Springer, Heidelberg (2002)
Mannor, S., Menache, I., Hoze, A., Klein, U.: Dynamic Abstraction in Reinforcement Learning via Clustering. In: Proceedings of the 21st International Conference on Machine Learning, pp. 560–567. ACM Press, New York (2004)
Simsek, O., Wolfe, A.P., Barto, A.G.: Identifying Useful Subgoals in Reinforcement Learning by Local Graph Partitioning. In: Proceedings of the 22th International Conference on Machine Learning, pp. 816–823. ACM Press, New York (2005)
Li, S., Kaiqi, Z., Guannan, D.: An Initialization Method for Fuzzy C-Means Clustering Algorithm Based on Grid and Density Weight. Computer Applications and Software 25(3), 22–23 (2008)
Lin, L.-j.: Self-improving agents based on reinforcement learning, planning and teaching. Machine Learning 321, 293–321 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hu, K., Yu, XL., Li, Z. (2011). Automatic Discovery of Subgoals Based on Improved FCM Clustering. In: Deng, H., Miao, D., Lei, J., Wang, F.L. (eds) Artificial Intelligence and Computational Intelligence. AICI 2011. Lecture Notes in Computer Science(), vol 7003. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23887-1_83
Download citation
DOI: https://doi.org/10.1007/978-3-642-23887-1_83
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23886-4
Online ISBN: 978-3-642-23887-1
eBook Packages: Computer ScienceComputer Science (R0)