Representing and solving factored markov decision processes with imprecise probabilities

Karina Valdivia Delgado, Leliane Nunes De Barros, Fabio Gagliardi Cozman, Ricardo Shirota

Research output: Contribution to conferenceConference Paper

8 Scopus citations

Abstract

This paper investigates Factored Markov Decision Processes with Imprecise Probabilities; that is, Markov Decision Processes where transition probabilities are imprecisely specified, and where their specification does not deal directly with states, but rather with factored representations of states. We first define a Factored MDPIP, based on a multilinear formulation for MDPIPs; then we propose a novel algorithm for generation of Γ-maximin policies for FactoredMDPIPs. We also developed a representation language for Factored MDPIPs (based on the standard PPDDL language); finally, we describe experiments with a problem of practical significance, the well-known System Administrator Planning problem.
Original languageAmerican English
Pages169-178
Number of pages10
StatePublished - 1 Dec 2009
Externally publishedYes
EventISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications -
Duration: 1 Dec 2009 → …

Conference

ConferenceISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications
Period1/12/09 → …

Fingerprint

Dive into the research topics of 'Representing and solving factored markov decision processes with imprecise probabilities'. Together they form a unique fingerprint.

Cite this