Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming

Thiago P. Bueno, Denis D. Mauá, Leliane N. De Barros, Fabio G. Cozman

Resultado de la investigación: Contribución a una conferenciaArtículo de conferencia

1 Cita (Scopus)

Resumen

Copyright © PMLR 2017. All rights reserved. We study languages that specify Markov Decision Processes with Imprecise Probabilities (MDPIPs) by mixing probabilities and logic programming. We propose a novel language that can capture MDPIPs and Markov Decision Processes with Set-valued Transitions (MDPSTs); we then obtain the complexity of one-step inference for the resulting MDPIPs and MDPSTs. We also present results of independent interest on the complexity of inference with probabilistic logic programs containing interval-valued probabilistic assessments. Finally, we also discuss policy generation techniques.
Idioma originalInglés estadounidense
Páginas49-60
Número de páginas12
EstadoPublicada - 1 ene 2019
Publicado de forma externa
EventoProceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 -
Duración: 1 ene 2019 → …

Conferencia

ConferenciaProceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017
Período1/01/19 → …

Huella Profundice en los temas de investigación de 'Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming'. En conjunto forman una huella única.

  • Citar esto

    Bueno, T. P., Mauá, D. D., De Barros, L. N., & Cozman, F. G. (2019). Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming. 49-60. Papel presentado en Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017, .