Resumen
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.
Idioma original | Inglés estadounidense |
---|---|
Páginas | 169-178 |
Número de páginas | 10 |
Estado | Publicada - 1 dic. 2009 |
Publicado de forma externa | Sí |
Evento | ISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications - Duración: 1 dic. 2009 → … |
Conferencia
Conferencia | ISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications |
---|---|
Período | 1/12/09 → … |