Abstract
In this paper we address the problem of explaining the recommendations generated by a Markov decision process (MDP). We propose an automatic explanation generation mechanism that is composed by two main stages. In the first stage, the most relevant variable given the current state is obtained, based on a factored representation of the MDP. The relevant variable is defined as the factor that has the greatest impact on the utility given certain state and action, and is a key element in the explanation generation mechanism. In the second stage, based on a general template, an explanation is generated by combing the information obtained from the MDP with domain knowledge represented as a frame system. The state and action given by the MDP, as well as the relevant variable, are used as pointers to the knowledge base to extract the relevant information and fill–in the explanation template. In this way, explanations of the recommendations given by the MDP can be generated on–line and incorporated to an intelligent assistant. We have evaluated this mechanism in an intelligent assistant for power plant operator training. The experimental results show that the automatically generated explanations are similar to those given by a domain expert.
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
Herrmann, J., Kloth, M., Feldkamp, F.: The role of explanation in an intelligent assistant system. In: Artificial Intelligence in Engineering, vol. 12, pp. 107–126. Elsevier Science Limited, Amsterdam (1998)
Druzdzel, M.: Explanation in probabilistic systems: Is it feasible? Will it work? In: Intelligent information systems V, Proc. of the workshop, Poland, pp. 12–24 (1991)
Renooij, S., van der Gaag, L.: Decision making in qualitative influence diagrams. In: Proceedings of the Eleventh International FLAIRS Conference, pp. 410–414. AAAI Press, Menlo Park (1998)
Lacave, C., Atienza, R., Díez, F.J.: Graphical explanations in Bayesian networks. In: Brause, R., Hanisch, E. (eds.) ISMDA 2000. LNCS, vol. 1933, pp. 122–129. Springer, Heidelberg (2000)
Bielza, C., del Pozo, J.F., Lucas, P.: Optimal decision explanation by extracting regularity patterns. In: Coenen, F., Preece, A., Macintosh, L. (eds.) Research and Development in Intelligent Systems XX, pp. 283–294. Springer, Heidelberg (2003)
Lacave, C., Luque, M., Díez, F.J.: Explanation of Bayesian networks and influence diagrams in Elvira. IEEE Transactions on Systems, Man and Cybernetics—Part B: Cybernetics 37, 952–965 (2007)
Givan, R., Dean, T., Greig, M.: Equivalence notions and model minimization in markov decision processes. Artif. Intell. 147(1-2), 163–223 (2003)
Dean, T., Givan, R.: Model minimization in markov decision processes. In: AAAI (ed.) Proceedings AAAI 1997, pp. 106–111. MIT Press, Cambridge (1997)
Munos, R., Moore, A.W.: Variable resolution discretization for high-accuracy solutions of optimal control problems. In: IJCAI 1999: Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, pp. 1348–1355. Morgan Kaufmann Publishers Inc., San Francisco (1999)
Khan, O.Z., Poupart, P., Black, J.: Explaining recommendations generated by MDPs. In: de Roth-Berghofer, T., et al. (eds.) 3rd International Workshop on Explanation-aware Computing ExaCt 2008, Proceedings of the 3rd International ExaCt Workshop, Patras, Greece (2008)
Puterman, M.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York (1994)
Bellman, R.E.: Dynamic Programming. Princeton U. Press, Princeton (1957)
Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: structural assumptions and computational leverage. Journal of AI Research 11, 1–94 (1999)
Minsky, M.: A framework for representing knowledge. In: Winston, P. (ed.) The Psychology of Computer Vision. McGraw-Hill, New York (1975)
Vadillo-Zorita, J., de Ilarraza, A.D., Fernández, I., Gutirrez, J., Elorriaga, J.: Explicaciones en sistemas tutores de entrenamiento: Representacion del dominio y estrategias de explicacion, Pais Vasco, España (1994)
Elizalde, F., Sucar, E., deBuen, P.: A Prototype of an intelligent assistant for operator’s training. In: International Colloquim for the Power Industry, Mexico, CIGRE-D2 (2005)
Lester, J.C., Porter, B.W.: Developing and empirically evaluating robust explanation generators: the knight experiments. Computational Linguistics 23(1), 65–101 (1997)
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
Elizalde, F., Sucar, E., Noguez, J., Reyes, A. (2009). Generating Explanations Based on Markov Decision Processes. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds) MICAI 2009: Advances in Artificial Intelligence. MICAI 2009. Lecture Notes in Computer Science(), vol 5845. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-05258-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-05258-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-05257-6
Online ISBN: 978-3-642-05258-3
eBook Packages: Computer ScienceComputer Science (R0)