Matches in SemOpenAlex for { <https://semopenalex.org/work/W1528120147> ?p ?o ?g. }
- W1528120147 endingPage "1249" @default.
- W1528120147 startingPage "1243" @default.
- W1528120147 abstract "We describe a point-based policy iteration (PBPI) algorithm for infinite-horizon POMDPs. PBPI replaces the exact policy improvement step of Hansen's policy iteration with point-based value iteration (PBVI). Despite being an approximate algorithm, PBPI is monotonic: At each iteration before convergence, PBPI produces a policy for which the values increase for at least one of a finite set of initial belief states, and decrease for none of these states. In contrast, PBVI cannot guarantee monotonic improvement of the value function or the policy. In practice PBPI generally needs a lower density of point coverage in the simplex and tends to produce superior policies with less computation. Experiments on several benchmark problems (up to 12,545 states) demonstrate the scalability and robustness of the PBPI algorithm." @default.
- W1528120147 created "2016-06-24" @default.
- W1528120147 creator A5016448581 @default.
- W1528120147 creator A5021682235 @default.
- W1528120147 creator A5036338045 @default.
- W1528120147 creator A5065859286 @default.
- W1528120147 creator A5081842202 @default.
- W1528120147 date "2007-07-22" @default.
- W1528120147 modified "2023-09-24" @default.
- W1528120147 title "Point-based policy iteration" @default.
- W1528120147 cites W1491973539 @default.
- W1528120147 cites W1494689917 @default.
- W1528120147 cites W1532688806 @default.
- W1528120147 cites W1701684472 @default.
- W1528120147 cites W2020609518 @default.
- W1528120147 cites W2034725503 @default.
- W1528120147 cites W2044375425 @default.
- W1528120147 cites W2103614073 @default.
- W1528120147 cites W2134802714 @default.
- W1528120147 cites W2144283793 @default.
- W1528120147 cites W2168359464 @default.
- W1528120147 cites W2963889160 @default.
- W1528120147 hasPublicationYear "2007" @default.
- W1528120147 type Work @default.
- W1528120147 sameAs 1528120147 @default.
- W1528120147 citedByCount "23" @default.
- W1528120147 countsByYear W15281201472012 @default.
- W1528120147 countsByYear W15281201472013 @default.
- W1528120147 countsByYear W15281201472014 @default.
- W1528120147 countsByYear W15281201472015 @default.
- W1528120147 countsByYear W15281201472017 @default.
- W1528120147 countsByYear W15281201472019 @default.
- W1528120147 countsByYear W15281201472020 @default.
- W1528120147 countsByYear W15281201472021 @default.
- W1528120147 crossrefType "proceedings-article" @default.
- W1528120147 hasAuthorship W1528120147A5016448581 @default.
- W1528120147 hasAuthorship W1528120147A5021682235 @default.
- W1528120147 hasAuthorship W1528120147A5036338045 @default.
- W1528120147 hasAuthorship W1528120147A5065859286 @default.
- W1528120147 hasAuthorship W1528120147A5081842202 @default.
- W1528120147 hasConcept C104317684 @default.
- W1528120147 hasConcept C105795698 @default.
- W1528120147 hasConcept C106189395 @default.
- W1528120147 hasConcept C11413529 @default.
- W1528120147 hasConcept C114614502 @default.
- W1528120147 hasConcept C126255220 @default.
- W1528120147 hasConcept C13280743 @default.
- W1528120147 hasConcept C134306372 @default.
- W1528120147 hasConcept C157449380 @default.
- W1528120147 hasConcept C159886148 @default.
- W1528120147 hasConcept C162324750 @default.
- W1528120147 hasConcept C185592680 @default.
- W1528120147 hasConcept C185798385 @default.
- W1528120147 hasConcept C205649164 @default.
- W1528120147 hasConcept C2777303404 @default.
- W1528120147 hasConcept C28826006 @default.
- W1528120147 hasConcept C33923547 @default.
- W1528120147 hasConcept C41008148 @default.
- W1528120147 hasConcept C45374587 @default.
- W1528120147 hasConcept C48044578 @default.
- W1528120147 hasConcept C50522688 @default.
- W1528120147 hasConcept C55493867 @default.
- W1528120147 hasConcept C61445026 @default.
- W1528120147 hasConcept C62438384 @default.
- W1528120147 hasConcept C63479239 @default.
- W1528120147 hasConcept C72169020 @default.
- W1528120147 hasConcept C77088390 @default.
- W1528120147 hasConceptScore W1528120147C104317684 @default.
- W1528120147 hasConceptScore W1528120147C105795698 @default.
- W1528120147 hasConceptScore W1528120147C106189395 @default.
- W1528120147 hasConceptScore W1528120147C11413529 @default.
- W1528120147 hasConceptScore W1528120147C114614502 @default.
- W1528120147 hasConceptScore W1528120147C126255220 @default.
- W1528120147 hasConceptScore W1528120147C13280743 @default.
- W1528120147 hasConceptScore W1528120147C134306372 @default.
- W1528120147 hasConceptScore W1528120147C157449380 @default.
- W1528120147 hasConceptScore W1528120147C159886148 @default.
- W1528120147 hasConceptScore W1528120147C162324750 @default.
- W1528120147 hasConceptScore W1528120147C185592680 @default.
- W1528120147 hasConceptScore W1528120147C185798385 @default.
- W1528120147 hasConceptScore W1528120147C205649164 @default.
- W1528120147 hasConceptScore W1528120147C2777303404 @default.
- W1528120147 hasConceptScore W1528120147C28826006 @default.
- W1528120147 hasConceptScore W1528120147C33923547 @default.
- W1528120147 hasConceptScore W1528120147C41008148 @default.
- W1528120147 hasConceptScore W1528120147C45374587 @default.
- W1528120147 hasConceptScore W1528120147C48044578 @default.
- W1528120147 hasConceptScore W1528120147C50522688 @default.
- W1528120147 hasConceptScore W1528120147C55493867 @default.
- W1528120147 hasConceptScore W1528120147C61445026 @default.
- W1528120147 hasConceptScore W1528120147C62438384 @default.
- W1528120147 hasConceptScore W1528120147C63479239 @default.
- W1528120147 hasConceptScore W1528120147C72169020 @default.
- W1528120147 hasConceptScore W1528120147C77088390 @default.
- W1528120147 hasLocation W15281201471 @default.
- W1528120147 hasOpenAccess W1528120147 @default.
- W1528120147 hasPrimaryLocation W15281201471 @default.
- W1528120147 hasRelatedWork W1484113995 @default.