| Texto completo | |
| Autor(es): |
Delgado, Karina Valdivia
[1]
;
de Barros, Leliane Nunes
[2]
;
Cozman, Fabio Gagliardi
[3]
;
Sanner, Scott
[4, 5]
Número total de Autores: 4
|
| Afiliação do(s) autor(es): | [1] Univ Sao Paulo, Escola Artes Ciencias & Humanidades, BR-05508 Sao Paulo - Brazil
[2] Univ Sao Paulo, Inst Matemat & Estat, BR-05508 Sao Paulo - Brazil
[3] Univ Sao Paulo, Escola Politecn, BR-05508 Sao Paulo - Brazil
[4] Australian Natl Univ, Canberra, ACT 2601 - Australia
[5] NICTA, Canberra, ACT 2601 - Australia
Número total de Afiliações: 5
|
| Tipo de documento: | Artigo Científico |
| Fonte: | INTERNATIONAL JOURNAL OF APPROXIMATE REASONING; v. 52, n. 7, p. 1000-1017, OCT 2011. |
| Citações Web of Science: | 3 |
| Resumo | |
This paper investigates Factored Markov Decision Processes with Imprecise Probabilities (MDPIPs); that is, Factored Markov Decision Processes (MDPs) where transition probabilities are imprecisely specified. We derive efficient approximate solutions for Factored MDPIPs based on mathematical programming. To do this, we extend previous linear programming approaches for linear approximations in Factored MDPs, resulting in a multilinear formulation for robust ``maximin{''} linear approximations in Factored MDPIPs. By exploiting the factored structure in MDPIPs we are able to demonstrate orders of magnitude reduction in solution time over standard exact non-factored approaches, in exchange for relatively low approximation errors, on a difficult class of benchmark problems with millions of states. (C) 2011 Elsevier Inc. All rights reserved. (AU) | |
| Processo FAPESP: | 08/03995-5 - LOGPROB: lógica probabilística - fundamentos e aplicações computacionais |
| Beneficiário: | Marcelo Finger |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |