Abstract
A Markov Decision Process (MDP) policy presents, for each state, an action, which preferably maximizes the expected reward accrual over time. In this paper, we present a novel system that generates, in real time, natural language explanations of the optimal action, recommended by an MDP while the user interacts with the MDP policy. We rely on natural language explanations in order to build trust between the user and the explanation system, leveraging existing research in psychology in order to generate salient explanations for the end user. Our explanation system is designed for portability between domains and uses a combination of domain specific and domain independent techniques. The system automatically extracts implicit knowledge from an MDP model and accompanying policy. This policy-based explanation system can be ported between applications without additional effort by knowledge engineers or model builders. Our system separates domain-specific data from the explanation logic, allowing for a robust system capable of incremental upgrades. Domain-specific explanations are generated through case-based explanation techniques specific to the domain and a knowledge base of concept mappings for our natural language model.
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
Aamodt, A., Plaza, E.: Case-based reasoning: Foundational issues, methodological variations, and system approaches. AI communications 7(1), 39–59 (1994)
Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)
Boutilier, C., Dean, T., Hanks, S.: Decision-theoretic planning: Structural assumptions and computational leverage. Journal of Artificial Intellgence Research 11, 1–94 (1999)
Camara, W.J., Echternacht, G.: The SAT I and high school grades: utility in predicting success in college. RN-10, College Entrance Examination Board, New York (2000)
Elizalde, F., Sucar, E., Noguez, J., Reyes, A.: Generating explanations based on markov decision processes. In: Aguirre, A.H., Borja, R.M., Garciá, C.A.R. (eds.) MICAI 2009. LNCS, vol. 5845, pp. 51–62. Springer, Heidelberg (2009)
Frederick, S., Loewenstein, G., O’Donoghue, T.: Time discounting and time preference: A critical review. Journal of Economic Literature 40, 351–401 (2002)
Guerin, J.T., Crawford, R., Goldsmith, J.: Constructing dynamic bayes nets using recommendation techniques from collaborative filtering. Tech report, University of Kentucky (2010)
Hoey, J., St-Aubin, R., Hu, A., Boutilier, C.: SPUDD: Stochastic planning using decision diagrams. In: Proc. UAI, pp. 279–288 (1999)
Khan, O., Poupart, P., Black, J.: Minimal sufficient explanations for factored Markov decision processes. In: Proc. ICAPS (2009)
Mathias, K., Williams, D., Cornett, A., Dekhtyar, A., Goldsmith, J.: Factored mdp elicitation and plan display. In: Proc. ISDN. AAAI, Menlo Park (2006)
Moore, B., Parker, R.: Critical Thinking. McGraw-Hill, New York (2008)
Mundhenk, M., Lusena, C., Goldsmith, J., Allender, E.: The complexity of finite-horizon Markov decision process problems. JACM 47(4), 681–720 (2000)
Murray, K., Häubl, G.: Interactive consumer decision aids. In: Wierenga, B. (ed.) Handbook of Marketing Decision Models, pp. 55–77. Springer, Heidelberg (2008)
Nugent, C., Doyle, D., Cunningham, P.: Gaining insight through case-based explanation. JIIS 32, 267–295 (2009)
Puterman, M.: Markov Decision Processes. Wiley, Chichester (1994)
Renooij, S.: Qualitative Approaches to Quantifying Probabilistic Networks. Ph.D. thesis, Institute for Information and Computing Sciences, Utrecht University, The Netherlands (2001)
Sinha, R., Swearingen, K.: The role of transparency in recommender systems. In: CHI 2002 Conference Companion, pp. 830–831 (2002)
Tversky, A., Kahneman, D.: Judgement under uncertainty: Heuristics and biases. Science 185, 1124–1131 (1974)
Tversky, A., Kahneman, D.: Rational choice and the framing of decisions. The Journal of Business 59(4), 251–278 (1986)
Tversky, A., Kahneman, D.: Advances in prospect theory: Cumulative representation of uncertainty. Journal of Risk and uncertainty 5(4), 297–323 (1992)
Witteman, C., Renooij, S., Koele, P.: Medicine in words and numbers: A cross-sectional survey comparing probability assessment scales. BMC Med. Informatics and Decision Making 7(13) (2007)
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
Dodson, T., Mattei, N., Goldsmith, J. (2011). A Natural Language Argumentation Interface for Explanation Generation in Markov Decision Processes. In: Brafman, R.I., Roberts, F.S., Tsoukià s, A. (eds) Algorithmic Decision Theory. ADT 2011. Lecture Notes in Computer Science(), vol 6992. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24873-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-24873-3_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24872-6
Online ISBN: 978-3-642-24873-3
eBook Packages: Computer ScienceComputer Science (R0)