Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming

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

Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming

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

Research output: Contribution to conference › Conference Paper

1 Scopus citations

Abstract

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.

Original language	American English
Pages	49-60
Number of pages	12
State	Published - 1 Jan 2019
Externally published	Yes
Event	Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 - Duration: 1 Jan 2019 → …

Conference

Conference	Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017
Period	1/01/19 → …

Cite this

@conference{818e1e9e5ce34e298ff3728841c878a8,

title = "Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming",

abstract = "Copyright {\textcopyright} 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.",

author = "Bueno, {Thiago P.} and Mau{\'a}, {Denis D.} and {De Barros}, {Leliane N.} and Cozman, {Fabio G.}",

year = "2019",

month = jan,

day = "1",

language = "American English",

pages = "49--60",

note = "Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017 ; Conference date: 01-01-2019",

}

Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming. / Bueno, Thiago P.; Mauá, Denis D.; De Barros, Leliane N.; Cozman, Fabio G.

2019. 49-60 Paper presented at Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017.

Research output: Contribution to conference › Conference Paper

TY - CONF

T1 - Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming

AU - Bueno, Thiago P.

AU - Mauá, Denis D.

AU - De Barros, Leliane N.

AU - Cozman, Fabio G.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85057239740&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85057239740&origin=inward

M3 - Conference Paper

SP - 49

EP - 60

T2 - Proceedings of the 10th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2017

Y2 - 1 January 2019

ER -

Modeling Markov decision processes with imprecise probabilities using probabilistic logic programming

Abstract

Conference

Other files and links

Fingerprint

Cite this