Multilinear and integer programming for markov decision processes with imprecise probabilities

Ricardo Shirota Filho, Fabio Gagliardi Cozman, Felipe Werndl Trevizan, Cassio Polpo De Campos, Leliane Nunes De Barros

Resultado de la investigación: Contribución a una conferenciaArtículo de conferencia

10 Citas (Scopus)

Resumen

Markov Decision Processes (MDPs) are extensively used to encode sequences of decisions with probabilistic effects. Markov Decision Processes with Imprecise Probabilities (MDPIPs) encode sequences of decisions whose effects are modeled using sets of probability distributions. In this paper we examine the computation of Γ-maximin policies for MDPIPs using multilinear and integer programming. We discuss the application of our algorithms to "factored" models and to a recent proposal, Markov Decision Processes with Set-valued Transitions (MDPSTs), that unifies the fields of probabilistic and "nondeterministic" planning in artificial intelligence research. Copyright © 2007 by SIPTA.
Idioma originalInglés estadounidense
Páginas395-404
Número de páginas10
EstadoPublicada - 1 dic 2007
Publicado de forma externa
EventoISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability: Theories and Applications -
Duración: 1 dic 2007 → …

Conferencia

ConferenciaISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability: Theories and Applications
Período1/12/07 → …

Huella Profundice en los temas de investigación de 'Multilinear and integer programming for markov decision processes with imprecise probabilities'. En conjunto forman una huella única.

  • Citar esto

    Filho, R. S., Cozman, F. G., Trevizan, F. W., De Campos, C. P., & De Barros, L. N. (2007). Multilinear and integer programming for markov decision processes with imprecise probabilities. 395-404. Papel presentado en ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability: Theories and Applications, .