Matches in SemOpenAlex for { <https://semopenalex.org/work/W1971034856> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W1971034856 endingPage "909" @default.
- W1971034856 startingPage "905" @default.
- W1971034856 abstract "Abstract This paper develops adaptive approach to the controlling observable Markov chains with a finite number of states. We apply Robust Mirror Descent Randomized Control Algorithm (RMDRCA) to a class of homogeneous finite Markov chains governed by the multi-armed bandit with unknown mean losses. It develops approach represented in [Nazin and Miller (2011a)] and [Nazin and Miller (2011b)]. As opposed to the partially observable Markov decision process an adaptive approach does not presuppose the knowledge of probabilistic characteristics of random perturbations and permits to obtain the control strategy with known rate of convergence to the optimal solution. We propose the concrete RMDRCA and prove the explicit, non-asymptotic upper bound for the mean losses at any current time. Numerical example illustrates theoretical results." @default.
- W1971034856 created "2016-06-24" @default.
- W1971034856 creator A5036133145 @default.
- W1971034856 creator A5048935741 @default.
- W1971034856 date "2013-01-01" @default.
- W1971034856 modified "2023-09-30" @default.
- W1971034856 title "Robust Mirror Decent Algorithm for a Multi-Armed Bandit Governed by a Stationary Finite Markov Chain" @default.
- W1971034856 cites W1974111631 @default.
- W1971034856 cites W1994647390 @default.
- W1971034856 cites W1997171717 @default.
- W1971034856 cites W2012020798 @default.
- W1971034856 cites W2044244166 @default.
- W1971034856 cites W2047514090 @default.
- W1971034856 cites W2078595922 @default.
- W1971034856 cites W2081787917 @default.
- W1971034856 cites W2125989409 @default.
- W1971034856 cites W2145707701 @default.
- W1971034856 cites W2166365115 @default.
- W1971034856 cites W3124678630 @default.
- W1971034856 cites W3157680351 @default.
- W1971034856 cites W6686365 @default.
- W1971034856 doi "https://doi.org/10.3182/20130619-3-ru-3018.00149" @default.
- W1971034856 hasPublicationYear "2013" @default.
- W1971034856 type Work @default.
- W1971034856 sameAs 1971034856 @default.
- W1971034856 citedByCount "0" @default.
- W1971034856 crossrefType "journal-article" @default.
- W1971034856 hasAuthorship W1971034856A5036133145 @default.
- W1971034856 hasAuthorship W1971034856A5048935741 @default.
- W1971034856 hasConcept C105795698 @default.
- W1971034856 hasConcept C11413529 @default.
- W1971034856 hasConcept C119857082 @default.
- W1971034856 hasConcept C121332964 @default.
- W1971034856 hasConcept C126255220 @default.
- W1971034856 hasConcept C1276947 @default.
- W1971034856 hasConcept C159886148 @default.
- W1971034856 hasConcept C199185054 @default.
- W1971034856 hasConcept C33923547 @default.
- W1971034856 hasConcept C41008148 @default.
- W1971034856 hasConcept C98763669 @default.
- W1971034856 hasConceptScore W1971034856C105795698 @default.
- W1971034856 hasConceptScore W1971034856C11413529 @default.
- W1971034856 hasConceptScore W1971034856C119857082 @default.
- W1971034856 hasConceptScore W1971034856C121332964 @default.
- W1971034856 hasConceptScore W1971034856C126255220 @default.
- W1971034856 hasConceptScore W1971034856C1276947 @default.
- W1971034856 hasConceptScore W1971034856C159886148 @default.
- W1971034856 hasConceptScore W1971034856C199185054 @default.
- W1971034856 hasConceptScore W1971034856C33923547 @default.
- W1971034856 hasConceptScore W1971034856C41008148 @default.
- W1971034856 hasConceptScore W1971034856C98763669 @default.
- W1971034856 hasIssue "9" @default.
- W1971034856 hasLocation W19710348561 @default.
- W1971034856 hasOpenAccess W1971034856 @default.
- W1971034856 hasPrimaryLocation W19710348561 @default.
- W1971034856 hasRelatedWork W141856251 @default.
- W1971034856 hasRelatedWork W1495764408 @default.
- W1971034856 hasRelatedWork W1965564958 @default.
- W1971034856 hasRelatedWork W2031153922 @default.
- W1971034856 hasRelatedWork W2049663053 @default.
- W1971034856 hasRelatedWork W2098336262 @default.
- W1971034856 hasRelatedWork W2128702080 @default.
- W1971034856 hasRelatedWork W2943366902 @default.
- W1971034856 hasRelatedWork W3198596521 @default.
- W1971034856 hasRelatedWork W287225487 @default.
- W1971034856 hasVolume "46" @default.
- W1971034856 isParatext "false" @default.
- W1971034856 isRetracted "false" @default.
- W1971034856 magId "1971034856" @default.
- W1971034856 workType "article" @default.