Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951700521> ?p ?o ?g. }
- W2951700521 abstract "This brief paper presents simple simulation-based algorithms for obtaining an approximately optimal policy in a given finite set in large finite constrained Markov decision processes. The algorithms are adapted from playing strategies for experts and bandits problem and their computational complexities are independent of state and action space sizes if the given policy set is relatively small. We establish convergence of their expected performances to the value of an optimal policy and convergence rates, and also almost-sure convergence to an optimal policy with an exponential rate for the algorithm adapted within the context of sleeping experts." @default.
- W2951700521 created "2019-06-27" @default.
- W2951700521 creator A5041693183 @default.
- W2951700521 date "2014-12-16" @default.
- W2951700521 modified "2023-09-27" @default.
- W2951700521 title "Sleeping Experts and Bandits Approach to Constrained Markov Decision Processes" @default.
- W2951700521 cites W1601081659 @default.
- W2951700521 cites W1969719302 @default.
- W2951700521 cites W1983916623 @default.
- W2951700521 cites W2008098735 @default.
- W2951700521 cites W2033413738 @default.
- W2951700521 cites W2045154709 @default.
- W2951700521 cites W2059984770 @default.
- W2951700521 cites W2069873069 @default.
- W2951700521 cites W2077789482 @default.
- W2951700521 cites W2100857832 @default.
- W2951700521 cites W2103012681 @default.
- W2951700521 cites W2116731530 @default.
- W2951700521 cites W2124839177 @default.
- W2951700521 hasPublicationYear "2014" @default.
- W2951700521 type Work @default.
- W2951700521 sameAs 2951700521 @default.
- W2951700521 citedByCount "0" @default.
- W2951700521 crossrefType "posted-content" @default.
- W2951700521 hasAuthorship W2951700521A5041693183 @default.
- W2951700521 hasConcept C105795698 @default.
- W2951700521 hasConcept C106189395 @default.
- W2951700521 hasConcept C119857082 @default.
- W2951700521 hasConcept C121332964 @default.
- W2951700521 hasConcept C126255220 @default.
- W2951700521 hasConcept C134306372 @default.
- W2951700521 hasConcept C151376022 @default.
- W2951700521 hasConcept C151730666 @default.
- W2951700521 hasConcept C159886148 @default.
- W2951700521 hasConcept C162324750 @default.
- W2951700521 hasConcept C162392398 @default.
- W2951700521 hasConcept C17098449 @default.
- W2951700521 hasConcept C177264268 @default.
- W2951700521 hasConcept C199360897 @default.
- W2951700521 hasConcept C26517878 @default.
- W2951700521 hasConcept C2777303404 @default.
- W2951700521 hasConcept C2779343474 @default.
- W2951700521 hasConcept C2780791683 @default.
- W2951700521 hasConcept C2983497884 @default.
- W2951700521 hasConcept C33923547 @default.
- W2951700521 hasConcept C38652104 @default.
- W2951700521 hasConcept C41008148 @default.
- W2951700521 hasConcept C50522688 @default.
- W2951700521 hasConcept C57869625 @default.
- W2951700521 hasConcept C62520636 @default.
- W2951700521 hasConcept C72434380 @default.
- W2951700521 hasConcept C86803240 @default.
- W2951700521 hasConcept C98763669 @default.
- W2951700521 hasConceptScore W2951700521C105795698 @default.
- W2951700521 hasConceptScore W2951700521C106189395 @default.
- W2951700521 hasConceptScore W2951700521C119857082 @default.
- W2951700521 hasConceptScore W2951700521C121332964 @default.
- W2951700521 hasConceptScore W2951700521C126255220 @default.
- W2951700521 hasConceptScore W2951700521C134306372 @default.
- W2951700521 hasConceptScore W2951700521C151376022 @default.
- W2951700521 hasConceptScore W2951700521C151730666 @default.
- W2951700521 hasConceptScore W2951700521C159886148 @default.
- W2951700521 hasConceptScore W2951700521C162324750 @default.
- W2951700521 hasConceptScore W2951700521C162392398 @default.
- W2951700521 hasConceptScore W2951700521C17098449 @default.
- W2951700521 hasConceptScore W2951700521C177264268 @default.
- W2951700521 hasConceptScore W2951700521C199360897 @default.
- W2951700521 hasConceptScore W2951700521C26517878 @default.
- W2951700521 hasConceptScore W2951700521C2777303404 @default.
- W2951700521 hasConceptScore W2951700521C2779343474 @default.
- W2951700521 hasConceptScore W2951700521C2780791683 @default.
- W2951700521 hasConceptScore W2951700521C2983497884 @default.
- W2951700521 hasConceptScore W2951700521C33923547 @default.
- W2951700521 hasConceptScore W2951700521C38652104 @default.
- W2951700521 hasConceptScore W2951700521C41008148 @default.
- W2951700521 hasConceptScore W2951700521C50522688 @default.
- W2951700521 hasConceptScore W2951700521C57869625 @default.
- W2951700521 hasConceptScore W2951700521C62520636 @default.
- W2951700521 hasConceptScore W2951700521C72434380 @default.
- W2951700521 hasConceptScore W2951700521C86803240 @default.
- W2951700521 hasConceptScore W2951700521C98763669 @default.
- W2951700521 hasLocation W29517005211 @default.
- W2951700521 hasOpenAccess W2951700521 @default.
- W2951700521 hasPrimaryLocation W29517005211 @default.
- W2951700521 hasRelatedWork W153346180 @default.
- W2951700521 hasRelatedWork W1640548472 @default.
- W2951700521 hasRelatedWork W2122187689 @default.
- W2951700521 hasRelatedWork W2132036095 @default.
- W2951700521 hasRelatedWork W2137497393 @default.
- W2951700521 hasRelatedWork W2150339816 @default.
- W2951700521 hasRelatedWork W2160067530 @default.
- W2951700521 hasRelatedWork W2211193316 @default.
- W2951700521 hasRelatedWork W2547823007 @default.
- W2951700521 hasRelatedWork W2735002392 @default.
- W2951700521 hasRelatedWork W2756126670 @default.
- W2951700521 hasRelatedWork W2781971850 @default.
- W2951700521 hasRelatedWork W2913022628 @default.
- W2951700521 hasRelatedWork W2963609347 @default.
- W2951700521 hasRelatedWork W2993527038 @default.
- W2951700521 hasRelatedWork W2996383434 @default.