Matches in SemOpenAlex for { <https://semopenalex.org/work/W2058455325> ?p ?o ?g. }
- W2058455325 abstract "We introduce exploration in the TD-learning algorithm to approximate the value function for a given policy. In this way we can modify the norm used for approximation, “zooming in” to a region of interest in the state space. We also provide extensions to SARSA to eliminate the need for numerical integration in policy improvement. Construction of the algorithm and its analysis build on recent general results concerning the spectral theory of Markov chains and positive operators." @default.
- W2058455325 created "2016-06-24" @default.
- W2058455325 creator A5047988825 @default.
- W2058455325 creator A5054958460 @default.
- W2058455325 date "2011-12-01" @default.
- W2058455325 modified "2023-10-16" @default.
- W2058455325 title "TD-learning with exploration" @default.
- W2058455325 cites W1979500760 @default.
- W2058455325 cites W1980019479 @default.
- W2058455325 cites W1983321045 @default.
- W2058455325 cites W1991470928 @default.
- W2058455325 cites W1995713768 @default.
- W2058455325 cites W1998172110 @default.
- W2058455325 cites W2014320009 @default.
- W2058455325 cites W2109762954 @default.
- W2058455325 cites W2110097348 @default.
- W2058455325 cites W2139418546 @default.
- W2058455325 cites W2150339816 @default.
- W2058455325 cites W2160698719 @default.
- W2058455325 cites W2168483803 @default.
- W2058455325 cites W2959560348 @default.
- W2058455325 cites W32403112 @default.
- W2058455325 cites W4211221179 @default.
- W2058455325 cites W4243772471 @default.
- W2058455325 cites W4302097244 @default.
- W2058455325 cites W565357261 @default.
- W2058455325 doi "https://doi.org/10.1109/cdc.2011.6160851" @default.
- W2058455325 hasPublicationYear "2011" @default.
- W2058455325 type Work @default.
- W2058455325 sameAs 2058455325 @default.
- W2058455325 citedByCount "4" @default.
- W2058455325 countsByYear W20584553252017 @default.
- W2058455325 countsByYear W20584553252020 @default.
- W2058455325 countsByYear W20584553252021 @default.
- W2058455325 countsByYear W20584553252022 @default.
- W2058455325 crossrefType "proceedings-article" @default.
- W2058455325 hasAuthorship W2058455325A5047988825 @default.
- W2058455325 hasAuthorship W2058455325A5054958460 @default.
- W2058455325 hasConcept C105795698 @default.
- W2058455325 hasConcept C106189395 @default.
- W2058455325 hasConcept C11413529 @default.
- W2058455325 hasConcept C119857082 @default.
- W2058455325 hasConcept C124913957 @default.
- W2058455325 hasConcept C126255220 @default.
- W2058455325 hasConcept C127413603 @default.
- W2058455325 hasConcept C14646407 @default.
- W2058455325 hasConcept C15336307 @default.
- W2058455325 hasConcept C154945302 @default.
- W2058455325 hasConcept C159886148 @default.
- W2058455325 hasConcept C17744445 @default.
- W2058455325 hasConcept C188116033 @default.
- W2058455325 hasConcept C191795146 @default.
- W2058455325 hasConcept C199539241 @default.
- W2058455325 hasConcept C33923547 @default.
- W2058455325 hasConcept C41008148 @default.
- W2058455325 hasConcept C50644808 @default.
- W2058455325 hasConcept C72434380 @default.
- W2058455325 hasConcept C78762247 @default.
- W2058455325 hasConcept C80444323 @default.
- W2058455325 hasConcept C91873725 @default.
- W2058455325 hasConcept C97541855 @default.
- W2058455325 hasConcept C98763669 @default.
- W2058455325 hasConceptScore W2058455325C105795698 @default.
- W2058455325 hasConceptScore W2058455325C106189395 @default.
- W2058455325 hasConceptScore W2058455325C11413529 @default.
- W2058455325 hasConceptScore W2058455325C119857082 @default.
- W2058455325 hasConceptScore W2058455325C124913957 @default.
- W2058455325 hasConceptScore W2058455325C126255220 @default.
- W2058455325 hasConceptScore W2058455325C127413603 @default.
- W2058455325 hasConceptScore W2058455325C14646407 @default.
- W2058455325 hasConceptScore W2058455325C15336307 @default.
- W2058455325 hasConceptScore W2058455325C154945302 @default.
- W2058455325 hasConceptScore W2058455325C159886148 @default.
- W2058455325 hasConceptScore W2058455325C17744445 @default.
- W2058455325 hasConceptScore W2058455325C188116033 @default.
- W2058455325 hasConceptScore W2058455325C191795146 @default.
- W2058455325 hasConceptScore W2058455325C199539241 @default.
- W2058455325 hasConceptScore W2058455325C33923547 @default.
- W2058455325 hasConceptScore W2058455325C41008148 @default.
- W2058455325 hasConceptScore W2058455325C50644808 @default.
- W2058455325 hasConceptScore W2058455325C72434380 @default.
- W2058455325 hasConceptScore W2058455325C78762247 @default.
- W2058455325 hasConceptScore W2058455325C80444323 @default.
- W2058455325 hasConceptScore W2058455325C91873725 @default.
- W2058455325 hasConceptScore W2058455325C97541855 @default.
- W2058455325 hasConceptScore W2058455325C98763669 @default.
- W2058455325 hasLocation W20584553251 @default.
- W2058455325 hasOpenAccess W2058455325 @default.
- W2058455325 hasPrimaryLocation W20584553251 @default.
- W2058455325 hasRelatedWork W2058455325 @default.
- W2058455325 hasRelatedWork W2124144580 @default.
- W2058455325 hasRelatedWork W2353483528 @default.
- W2058455325 hasRelatedWork W2569146624 @default.
- W2058455325 hasRelatedWork W2785733479 @default.
- W2058455325 hasRelatedWork W2808418668 @default.
- W2058455325 hasRelatedWork W2937181779 @default.
- W2058455325 hasRelatedWork W3167472281 @default.
- W2058455325 hasRelatedWork W4308702637 @default.
- W2058455325 hasRelatedWork W616059226 @default.
- W2058455325 isParatext "false" @default.