Representing and solving factored markov decision processes with imprecise probabilities

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

Resultado de la investigación: Contribución a una conferenciaArtículo de conferencia

8 Citas (Scopus)

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 originalInglés estadounidense
Páginas169-178
Número de páginas10
EstadoPublicada - 1 dic 2009
Publicado de forma externa
EventoISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications -
Duración: 1 dic 2009 → …

Conferencia

ConferenciaISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications
Período1/12/09 → …

Huella Profundice en los temas de investigación de 'Representing and solving factored markov decision processes with imprecise probabilities'. En conjunto forman una huella única.

  • Citar esto

    Delgado, K. V., De Barros, L. N., Cozman, F. G., & Shirota, R. (2009). Representing and solving factored markov decision processes with imprecise probabilities. 169-178. Papel presentado en ISIPTA 2009 - Proceedings of the 6th International Symposium on Imprecise Probability: Theories and Applications, .