Matches in SemOpenAlex for { <https://semopenalex.org/work/W2145182198> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2145182198 endingPage "1088" @default.
- W2145182198 startingPage "1082" @default.
- W2145182198 abstract "We propose and analyze an algorithm that approximates solutions to the problem of optimal stopping in a discounted irreducible aperiodic Markov chain. The scheme involves the use of linear combinations of fixed basis functions to approximate a Q-function. The weights of the linear combination are incrementally updated through an iterative process similar to Q-learning, involving simulation of the underlying Markov chain. Due to space limitations, we only provide an overview of a proof of convergence (with probability 1) and bounds on the approximation error. This is the first theoretical result that establishes the soundness of a Q-learning-like algorithm when combined with arbitrary linear function approximators to solve a sequential decision problem. Though this paper focuses on the case of finite state spaces, the results extend naturally to continuous and unbounded state spaces, which are addressed in a forthcoming full-length paper." @default.
- W2145182198 created "2016-06-24" @default.
- W2145182198 creator A5032630894 @default.
- W2145182198 creator A5045543562 @default.
- W2145182198 date "1996-12-03" @default.
- W2145182198 modified "2023-09-25" @default.
- W2145182198 title "Approximate Solutions to Optimal Stopping Problems" @default.
- W2145182198 cites W1547105496 @default.
- W2145182198 cites W1568229137 @default.
- W2145182198 cites W2098432798 @default.
- W2145182198 cites W2100677568 @default.
- W2145182198 cites W2115849850 @default.
- W2145182198 cites W2139418546 @default.
- W2145182198 cites W2147750403 @default.
- W2145182198 cites W2165131254 @default.
- W2145182198 cites W2169982856 @default.
- W2145182198 cites W3011120880 @default.
- W2145182198 hasPublicationYear "1996" @default.
- W2145182198 type Work @default.
- W2145182198 sameAs 2145182198 @default.
- W2145182198 citedByCount "2" @default.
- W2145182198 crossrefType "proceedings-article" @default.
- W2145182198 hasAuthorship W2145182198A5032630894 @default.
- W2145182198 hasAuthorship W2145182198A5045543562 @default.
- W2145182198 hasConcept C104247578 @default.
- W2145182198 hasConcept C105795698 @default.
- W2145182198 hasConcept C106189395 @default.
- W2145182198 hasConcept C114614502 @default.
- W2145182198 hasConcept C12426560 @default.
- W2145182198 hasConcept C126255220 @default.
- W2145182198 hasConcept C14036430 @default.
- W2145182198 hasConcept C159886148 @default.
- W2145182198 hasConcept C162324750 @default.
- W2145182198 hasConcept C199360897 @default.
- W2145182198 hasConcept C2524010 @default.
- W2145182198 hasConcept C2777303404 @default.
- W2145182198 hasConcept C28826006 @default.
- W2145182198 hasConcept C33923547 @default.
- W2145182198 hasConcept C39920170 @default.
- W2145182198 hasConcept C41008148 @default.
- W2145182198 hasConcept C50522688 @default.
- W2145182198 hasConcept C72434380 @default.
- W2145182198 hasConcept C78458016 @default.
- W2145182198 hasConcept C86803240 @default.
- W2145182198 hasConcept C98763669 @default.
- W2145182198 hasConcept C99414536 @default.
- W2145182198 hasConceptScore W2145182198C104247578 @default.
- W2145182198 hasConceptScore W2145182198C105795698 @default.
- W2145182198 hasConceptScore W2145182198C106189395 @default.
- W2145182198 hasConceptScore W2145182198C114614502 @default.
- W2145182198 hasConceptScore W2145182198C12426560 @default.
- W2145182198 hasConceptScore W2145182198C126255220 @default.
- W2145182198 hasConceptScore W2145182198C14036430 @default.
- W2145182198 hasConceptScore W2145182198C159886148 @default.
- W2145182198 hasConceptScore W2145182198C162324750 @default.
- W2145182198 hasConceptScore W2145182198C199360897 @default.
- W2145182198 hasConceptScore W2145182198C2524010 @default.
- W2145182198 hasConceptScore W2145182198C2777303404 @default.
- W2145182198 hasConceptScore W2145182198C28826006 @default.
- W2145182198 hasConceptScore W2145182198C33923547 @default.
- W2145182198 hasConceptScore W2145182198C39920170 @default.
- W2145182198 hasConceptScore W2145182198C41008148 @default.
- W2145182198 hasConceptScore W2145182198C50522688 @default.
- W2145182198 hasConceptScore W2145182198C72434380 @default.
- W2145182198 hasConceptScore W2145182198C78458016 @default.
- W2145182198 hasConceptScore W2145182198C86803240 @default.
- W2145182198 hasConceptScore W2145182198C98763669 @default.
- W2145182198 hasConceptScore W2145182198C99414536 @default.
- W2145182198 hasLocation W21451821981 @default.
- W2145182198 hasOpenAccess W2145182198 @default.
- W2145182198 hasPrimaryLocation W21451821981 @default.
- W2145182198 hasRelatedWork W1788877992 @default.
- W2145182198 hasRelatedWork W2051021044 @default.
- W2145182198 hasRelatedWork W2055962914 @default.
- W2145182198 hasRelatedWork W2085218742 @default.
- W2145182198 hasRelatedWork W2114383819 @default.
- W2145182198 hasRelatedWork W2120045945 @default.
- W2145182198 hasRelatedWork W2141512970 @default.
- W2145182198 hasRelatedWork W2153227067 @default.
- W2145182198 hasRelatedWork W2283643534 @default.
- W2145182198 hasRelatedWork W23780305 @default.
- W2145182198 hasRelatedWork W2552244163 @default.
- W2145182198 hasRelatedWork W2568914482 @default.
- W2145182198 hasRelatedWork W2619414566 @default.
- W2145182198 hasRelatedWork W2879935397 @default.
- W2145182198 hasRelatedWork W2908026254 @default.
- W2145182198 hasRelatedWork W2941993860 @default.
- W2145182198 hasRelatedWork W2947012451 @default.
- W2145182198 hasRelatedWork W3006595078 @default.
- W2145182198 hasRelatedWork W3101875681 @default.
- W2145182198 hasRelatedWork W3147478359 @default.
- W2145182198 hasVolume "9" @default.
- W2145182198 isParatext "false" @default.
- W2145182198 isRetracted "false" @default.
- W2145182198 magId "2145182198" @default.
- W2145182198 workType "article" @default.