Abstract
This paper introduces an approach to reinforcement learning by cooperating agents using a near set-based variation of the Peters-Henry-Lockery rough set-based actor critic adaptive learning method. Near sets were introduced by James Peters in 2006 and formally defined in 2007. Near sets result from a generalization of rough set theory. One set X is near another set Y to the extent that the description of at least one of the objects in X matches the description of at least one of the objects in Y. The hallmark of near set theory is object description and the classification of objects by means of features. Rough sets were introduced by Zdzisław Pawlak during the early 1980s and provide a basis for perception of objects viewed on the level of classes rather than the level of individual objects. A fundamental basis for near set as well as rough set theory is the approximation of one set by another set considered in the context of approximation spaces. It was observed by Ewa Orłowska in 1982 that approximation spaces serve as a formal counterpart of perception, or observation. This article extends earlier work on an ethology-based Peters-Henry-Lockery actor critic method that is episodic and is defined in the context of an approximation space. The contribution of this article is a framework for actor-critic learning defined in the context of near sets. This paper also reports the results of experiments with three different forms of the actor critic method.
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
Lockery, D., Peters, J.F.: Adaptive learning by a target tracking system. Int. J. of Intelligent Computing and Cybernetics 1, 1–28 (2008)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Peters, J.F.: Rough Ethology: Towards a biologically inspired study of collective behavior in Intelligent System with Approximation Spaces. In: Peters, J.F., Skowron, A. (eds.) Transactions on Rough Sets III. LNCS, vol. 3400, pp. 153–174. Springer, Heidelberg (2005)
Peters, J.F., Henry, C., Gunderson, D.S.: Biologically-inspired approximate adaptive learning control strategies: A rough set approach. International Journal of Hybrid Intelligent Systems 4(4), 203–216 (2007)
Peters, J.F., Skowron, A., Stepaniuk, J.: Nearness of Objects: Extension of Approximation Space Model. Fundamenta Informaticae 79(3-4), 497–512 (2007)
Peters, J.F., Skowron, A., Stepaniuk, J.: Nearness in approximation spaces. In: Lindemann, G., Schlilngloff, H., et al. (eds.) Proc. Concurrency, Specification & Programming. Informatik-Berichte 2006, Humboldt-Universität zu, Berlin, pp. 434–445 (2006)
Peters, J.F., Henry, C.: Reinforcement Learning with approximation Spaces. Fundamental Informaticae 71(2-3), 323–349 (2006)
Peters, J.F., Ramanna, S.: Feature Selection: Near Set Approach. In: Ras, Z.W., Tsumoto, S., Zighed, D.A. (eds.) 3rd Int. Workshop on Mining Complex Data (MCD 2007), ECML/PKDD-2007, vol. 4484, pp. 57–71. Springer, Heidelberg (2007)
Gibbs, J.W.: Elementary Principles in Statistical Mechanics. Dover, NY (1960)
Pawlak, Z.: Rough Sets, Institute for Computer Science, Polish Academy of Sciences, Report 431 (March 1981)
Pawlak, Z.: Classification of Objects by Means of Attributes, Institute for Computer Science, Polish Academy of Sciences, Report 429 (March 1981)
Pawlak, Z., Skowron, A.: Rudiments of rough sets. Information Sciences. An International Journal 177(1), 3–27 (2007)
Orlowska, E.: Applications of Rough Sets, Semantics of Vague Concepts, Institute for Computer Science, Polish Academy of Sciences, Report 469 (March 1982); Dorn, G., Weingartner, P.: Foundations of Logic and Linguistics. Problems and Solutions, March 1982, pp. 465–482. Plenum Press, London (1985)
Peters, J.F.: Classification of Perceptual Objects by Means of Features. Int. J. of Information Technology and Intelligent Computing 3(2), 1–35 (2007)
Peters, J.F., Shahfar, S., Ramanna, S., Szturm, T.: Biologically-inspired adaptive learning: A near set approach. In: Proc. Frontiers in the Convergence of Bioscience and Information Technologies,10.1109/FBIT.2007.39, pp. 403–408 (2007)
Peters, J.F.: Near Sets. Special Theory about Nearness of Objects. Fundamenta Informaticae 76, 1–27 (2006)
Peters, J.F.: Near sets. General theory about nearness of objects. Applied Mathematical Sciences 1(53), 2609–2029 (2007), http://wren.ece.umanitoba.ca/
Peters, J.F., Wasilewski, P.: Foundations of near sets. Information Sciences (submitted, 2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Anwar, S., Patnaik, K.S. (2008). Actor Critic Learning: A Near Set Approach. In: Chan, CC., Grzymala-Busse, J.W., Ziarko, W.P. (eds) Rough Sets and Current Trends in Computing. RSCTC 2008. Lecture Notes in Computer Science(), vol 5306. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88425-5_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-88425-5_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88423-1
Online ISBN: 978-3-540-88425-5
eBook Packages: Computer ScienceComputer Science (R0)