Abstract
This paper proposes an unifying formulation for nondeterministic and probabilistic planning. These two strands of AI planning have followed different strategies: while nondeterministic planning usually looks for minimax (or worst-case) policies, probabilistic planning attempts to maximize expected reward. In this paper we show that both problems are special cases of a more general approach, and we demonstrate that the resulting structures are Markov Decision Processes with Imprecise Probabilities (MDPIPs). We also show how existing algorithms for MDPIPs can be adapted to planning under uncertainty.
Project funded by Fundação de Amparo a Pesquisa do Estado de São Paulo (FAPESP) process number 04/09568-0.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Ghallab, M., Nau, D., Traverso, P.: Automated Planning: Theory & Practice. Morgan Kaufmann, San Francisco (2004)
Bonet, B., Geffner, H.: Learning Depth-First Search: A unified approach to heuristic search in deterministic and non-deterministic settings, and its application to MDPs. In: ICAPS (2006) (to appear)
Bonet, B., Geffner, H.: Labeled RTDP: Improving the convergence of real-time dynamic programming. In: ICAPS, Trento, Italy, pp. 12–21. AAAI Press, Menlo Park (2003)
Guestrin, C., Koller, D., Parr, R., Venkataraman, S.: Efficient solution algorithms for factored MDPs. J. Artif. Intell. Res (JAIR) 19, 399–468 (2003)
Bertoli, P., Cimatti, A., Roveri, M., Traverso, P.: Planning in nondeterministic domains under partial observability via symbolic model checking. In: IJCAI, pp. 473–478 (2001)
Bonet, B., Geffner, H.: Planning with incomplete information as heuristic search in belief space. In: ICAPS, Breckenridge, CO, pp. 52–61. AAAI Press, Menlo Park (2000)
Luce, D., Raiffa, H.: Games and Decisions. Dover edn., Mineola (1957)
Berger, J.O.: Statistical Decision Theory and Bayesian Analysis. Springer, Heidelberg (1985)
Knight, F.H.: Risk, Uncertainty, and Profit. Hart, Schaffner & Marx. Houghton Mifflin Company, Boston (1921)
Levi, I.: The Enterprise of Knowledge. MIT Press, Cambridge (1980)
Walley, P.: Statistical Reasoning with Imprecise Probabilities. Chapman and Hall, London (1991)
Walley, P.: Measures of uncertainty in expert systems. AI 83, 1–58 (1996)
Seidenfeld, T., Kadane, J.B., Schervish, M.J.: On the shared preferences of two Bayesian decision makers. The Journal of Philosophy 86(5), 225–244 (1989)
Seidenfeld, T., Schervish, M.: Two perspectives on consensus for (Bayesian) inference and decisions. IEEE Transactions on Systems, Man and Cybernetics 20(1), 318–325 (1990)
Huber, P.J.: Robust Statistics. Wiley, New York (1980)
Kadane, J.B. (ed.): Robustness of Bayesian Analyses. Studies in Bayesian econometrics, vol. 4. Elsevier Science Pub. Co., New York (1984)
Frisch, A.M., Haddawy, P.: Anytime deduction for probabilistic logic. Artificial Intelligence 69, 93–122 (1994)
Halpern, J.Y.: Reasoning about uncertainty. MIT Press, Cambridge (2003)
Nilsson, N.J.: Probabilistic logic. Artificial Intelligence 28, 71–87 (1986)
Shafer, G.: A Mathematical Theory of Evidence. Princeton University Press, Princeton (1976)
Anrig, B., Bissig, R., Haenni, R., Kohlas, J., Lehmann, N.: Probabilistic argumentation systems: Introduction to assumption-based modeling with ABEL. Technical Report 99-1, Institute of Informatics, University of Fribourg (1999)
Cozman, F.G.: Credal networks. AI 120, 199–233 (2000)
Cozman, F.G.: Graphical models for imprecise probabilities. International Journal of Approximate Reasoning 39(2-3), 167–184 (2005)
Fagiuoli, E., Zaffalon, M.: 2U: An exact interval propagation algorithm for polytrees with binary variables. Artificial Intelligence 106(1), 77–107 (1998)
de Cooman, G., Cozman, F., Moral, S., Walley, P. (eds.): Proceedings of the First International Symposium on Imprecise Probabilities and Their Applications (SIPTA), Universiteit Gent, Ghent, Belgium (1999)
de Cooman, G., Fine, T.L., Seidenfeld, T.: Proceedings of the 2nd International SIPTA. Shaker Publishing, The Netherlands (2001)
Bernard, J.M., Seidenfeld, T., Zaffalon, M. (eds.): Proceedings of the 3rd International SIPTA Carleton Scientific, Lugano, Switzerland (2003)
Cozman, F.G., Nau, R., Seidenfeld, T.: Proceedings of the Fourth International Symposium on Imprecise Probabilities and Their Applications. SIPTA (2005)
White III, C.C., Eldeib, H.K.: Markov decision processes with imprecise transition probabilities. Operations Research 42(4), 739–749 (1994)
Satia, J.K., Lave Jr., R.E.: Markovian decision processes with uncertain transition probabilities. Operations Research 21(3), 728–740 (1973)
Howard, R.A.: Dynamic Porgramming and Markov Processes. MIT Press, Cambridge (1960)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Trevizan, F.W., Cozman, F.G., de Barros, L.N. (2006). Unifying Nondeterministic and Probabilistic Planning Through Imprecise Markov Decision Processes. In: Sichman, J.S., Coelho, H., Rezende, S.O. (eds) Advances in Artificial Intelligence - IBERAMIA-SBIA 2006. IBERAMIA SBIA 2006 2006. Lecture Notes in Computer Science(), vol 4140. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11874850_54
Download citation
DOI: https://doi.org/10.1007/11874850_54
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45462-5
Online ISBN: 978-3-540-45464-9
eBook Packages: Computer ScienceComputer Science (R0)