Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950360068> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2950360068 abstract "This paper addresses the issue of policy evaluation in Markov Decision Processes, using linear function approximation. It provides a unified view of algorithms such as TD(lambda), LSTD(lambda), iLSTD, residual-gradient TD. It is asserted that they all consist in minimizing a gradient function and differ by the form of this function and their means of minimizing it. Two new schemes are introduced in that framework: Full-gradient TD which uses a generalization of the principle introduced in iLSTD, and EGD TD, which reduces the gradient by successive equi-gradient descents. These three algorithms form a new intermediate family with the interesting property of making much better use of the samples than TD while keeping a gradient descent scheme, which is useful for complexity issues and optimistic policy iteration." @default.
- W2950360068 created "2019-06-27" @default.
- W2950360068 creator A5021012307 @default.
- W2950360068 creator A5087891858 @default.
- W2950360068 date "2006-11-29" @default.
- W2950360068 modified "2023-09-27" @default.
- W2950360068 title "A Unified View of TD Algorithms; Introducing Full-Gradient TD and Equi-Gradient Descent TD" @default.
- W2950360068 cites W1507222174 @default.
- W2950360068 cites W1646707810 @default.
- W2950360068 cites W2121863487 @default.
- W2950360068 cites W2139418546 @default.
- W2950360068 cites W86816279 @default.
- W2950360068 hasPublicationYear "2006" @default.
- W2950360068 type Work @default.
- W2950360068 sameAs 2950360068 @default.
- W2950360068 citedByCount "1" @default.
- W2950360068 crossrefType "posted-content" @default.
- W2950360068 hasAuthorship W2950360068A5021012307 @default.
- W2950360068 hasAuthorship W2950360068A5087891858 @default.
- W2950360068 hasConcept C105795698 @default.
- W2950360068 hasConcept C106189395 @default.
- W2950360068 hasConcept C111472728 @default.
- W2950360068 hasConcept C11413529 @default.
- W2950360068 hasConcept C115680565 @default.
- W2950360068 hasConcept C116149140 @default.
- W2950360068 hasConcept C126255220 @default.
- W2950360068 hasConcept C134306372 @default.
- W2950360068 hasConcept C138885662 @default.
- W2950360068 hasConcept C14036430 @default.
- W2950360068 hasConcept C153258448 @default.
- W2950360068 hasConcept C154945302 @default.
- W2950360068 hasConcept C155512373 @default.
- W2950360068 hasConcept C159886148 @default.
- W2950360068 hasConcept C177148314 @default.
- W2950360068 hasConcept C189950617 @default.
- W2950360068 hasConcept C206688291 @default.
- W2950360068 hasConcept C28826006 @default.
- W2950360068 hasConcept C33923547 @default.
- W2950360068 hasConcept C41008148 @default.
- W2950360068 hasConcept C50644808 @default.
- W2950360068 hasConcept C77618280 @default.
- W2950360068 hasConcept C78458016 @default.
- W2950360068 hasConcept C86803240 @default.
- W2950360068 hasConceptScore W2950360068C105795698 @default.
- W2950360068 hasConceptScore W2950360068C106189395 @default.
- W2950360068 hasConceptScore W2950360068C111472728 @default.
- W2950360068 hasConceptScore W2950360068C11413529 @default.
- W2950360068 hasConceptScore W2950360068C115680565 @default.
- W2950360068 hasConceptScore W2950360068C116149140 @default.
- W2950360068 hasConceptScore W2950360068C126255220 @default.
- W2950360068 hasConceptScore W2950360068C134306372 @default.
- W2950360068 hasConceptScore W2950360068C138885662 @default.
- W2950360068 hasConceptScore W2950360068C14036430 @default.
- W2950360068 hasConceptScore W2950360068C153258448 @default.
- W2950360068 hasConceptScore W2950360068C154945302 @default.
- W2950360068 hasConceptScore W2950360068C155512373 @default.
- W2950360068 hasConceptScore W2950360068C159886148 @default.
- W2950360068 hasConceptScore W2950360068C177148314 @default.
- W2950360068 hasConceptScore W2950360068C189950617 @default.
- W2950360068 hasConceptScore W2950360068C206688291 @default.
- W2950360068 hasConceptScore W2950360068C28826006 @default.
- W2950360068 hasConceptScore W2950360068C33923547 @default.
- W2950360068 hasConceptScore W2950360068C41008148 @default.
- W2950360068 hasConceptScore W2950360068C50644808 @default.
- W2950360068 hasConceptScore W2950360068C77618280 @default.
- W2950360068 hasConceptScore W2950360068C78458016 @default.
- W2950360068 hasConceptScore W2950360068C86803240 @default.
- W2950360068 hasLocation W29503600681 @default.
- W2950360068 hasOpenAccess W2950360068 @default.
- W2950360068 hasPrimaryLocation W29503600681 @default.
- W2950360068 hasRelatedWork W1931293201 @default.
- W2950360068 hasRelatedWork W2130314481 @default.
- W2950360068 hasRelatedWork W2130906191 @default.
- W2950360068 hasRelatedWork W2391858684 @default.
- W2950360068 hasRelatedWork W2537365322 @default.
- W2950360068 hasRelatedWork W2548231749 @default.
- W2950360068 hasRelatedWork W2758197809 @default.
- W2950360068 hasRelatedWork W2772649491 @default.
- W2950360068 hasRelatedWork W2783940602 @default.
- W2950360068 hasRelatedWork W2806265408 @default.
- W2950360068 hasRelatedWork W2951143668 @default.
- W2950360068 hasRelatedWork W2965025199 @default.
- W2950360068 hasRelatedWork W2997011652 @default.
- W2950360068 hasRelatedWork W2997803752 @default.
- W2950360068 hasRelatedWork W3006555440 @default.
- W2950360068 hasRelatedWork W3081204256 @default.
- W2950360068 hasRelatedWork W3102695845 @default.
- W2950360068 hasRelatedWork W3160101512 @default.
- W2950360068 hasRelatedWork W3199147165 @default.
- W2950360068 hasRelatedWork W3201944662 @default.
- W2950360068 isParatext "false" @default.
- W2950360068 isRetracted "false" @default.
- W2950360068 magId "2950360068" @default.
- W2950360068 workType "article" @default.