Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities

Скорочена інформація про документ
dc.contributor.authorZgurovsky, M. Z.
dc.contributor.authorKasyanov, P. O.
dc.contributor.authorFeinberg, E. A.
dc.contributor.authorЗгуровський, Михайло Захарович
dc.contributor.authorКасьянов, Павло Олегович
dc.date.accessioned2017-06-29T09:16:07Z
dc.date.available2017-06-29T09:16:07Z
dc.date.issued2016
dc.description.abstractenThis paper describes sufficient conditions for the existence of optimal policies for partially observable Markov decision processes (POMDPs) with Borel state, observation, and action sets, when the goal is to minimize the expected total costs over finite or infinite horizons. For infinite-horizon problems, one-step costs are either discounted or assumed to be nonnegative. Action sets may be noncompact and one-step cost functions may be unbounded. The introduced conditions are also sufficient for the validity of optimality equations, semicontinuity of value functions, and convergence of value iterations to optimal values. Since POMDPs can be reduced to completely observable Markov decision processes (COMDPs), whose states are posterior state distributions, this paper focuses on the validity of the above-mentioned optimality properties for COMDPs. The central question is whether the transition probabilities for the COMDP are weakly continuous. We introduce sufficient conditions for this and show that the transition probabilities for a COMDP are weakly continuous, if transition probabilities of the underlying Markov decision process are weakly continuous and observation probabilities for the POMDP are continuous in total variation. Moreover, the continuity in total variation of the observation probabilities cannot be weakened to setwise continuity. The results are illustrated with counterexamples and examples.uk
dc.format.pagerangeP. 656–681uk
dc.identifier.citationZgurovsky, M. Z. Partially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities / Michael Z. Zgurovsky, Eugene A. Feinberg, Pavlo O. Kasyanov // Mathematics of operations research. – Vol. 41, No. 2. – 2016. – P. 656–681. – DOI: 10.1287/moor.2015.0746uk
dc.identifier.doi10.1287/moor.2015.0746
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/19880
dc.language.isoenuk
dc.source.nameMathematics of operations research. – Vol. 41. – No. 2. – 2016.uk
dc.status.pubpublisheduk
dc.subjectpartially observable Markov decision processesuk
dc.subjecttotal costuk
dc.subjectoptimality inequalityuk
dc.subjectoptimal policyuk
dc.titlePartially Observable Total-Cost Markov Decision Processes with Weakly Continuous Transition Probabilitiesuk
dc.typeArticleuk
thesis.degree.level-uk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
feinberg2016.pdf
Розмір:
453.97 KB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
7.8 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Статті (ММСА)