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 original||Inglés estadounidense|
|Número de páginas||12|
|Estado||Publicada - 1 ene 2019|
|Publicado de forma externa||Sí|
|Evento||Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 - |
Duración: 1 ene 2019 → …
|Conferencia||Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017|
|Período||1/01/19 → …|
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, .