Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040497714> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3040497714 abstract "We propose a principled kernel-based policy iteration algorithm to solve the continuous-state Markov Decision Processes (MDPs). In contrast to most decision-theoretic planning frameworks, which assume fully known state transition models, we design a method that eliminates such a strong assumption, which is oftentimes extremely difficult to engineer in reality. To achieve this, we first apply the second-order Taylor expansion of the value function. The Bellman optimality equation is then approximated by a partial differential equation, which only relies on the first and second moments of the transition model. By combining the kernel representation of value function, we then design an efficient policy iteration algorithm whose policy evaluation step can be represented as a linear system of equations characterized by a finite set of supporting states. We have validated the proposed method through extensive simulations in both simplified and realistic planning scenarios, and the experiments show that our proposed approach leads to a much superior performance over several baseline methods." @default.
- W3040497714 created "2020-07-10" @default.
- W3040497714 creator A5013116707 @default.
- W3040497714 creator A5056666350 @default.
- W3040497714 creator A5075854198 @default.
- W3040497714 date "2020-07-12" @default.
- W3040497714 modified "2023-09-27" @default.
- W3040497714 title "Kernel Taylor-Based Value Function Approximation for Continuous-State Markov Decision Processes" @default.
- W3040497714 doi "https://doi.org/10.15607/rss.2020.xvi.050" @default.
- W3040497714 hasPublicationYear "2020" @default.
- W3040497714 type Work @default.
- W3040497714 sameAs 3040497714 @default.
- W3040497714 citedByCount "1" @default.
- W3040497714 countsByYear W30404977142023 @default.
- W3040497714 crossrefType "proceedings-article" @default.
- W3040497714 hasAuthorship W3040497714A5013116707 @default.
- W3040497714 hasAuthorship W3040497714A5056666350 @default.
- W3040497714 hasAuthorship W3040497714A5075854198 @default.
- W3040497714 hasBestOaLocation W30404977141 @default.
- W3040497714 hasConcept C105795698 @default.
- W3040497714 hasConcept C106189395 @default.
- W3040497714 hasConcept C106666656 @default.
- W3040497714 hasConcept C114614502 @default.
- W3040497714 hasConcept C119857082 @default.
- W3040497714 hasConcept C126255220 @default.
- W3040497714 hasConcept C134306372 @default.
- W3040497714 hasConcept C14646407 @default.
- W3040497714 hasConcept C158946198 @default.
- W3040497714 hasConcept C159886148 @default.
- W3040497714 hasConcept C163836022 @default.
- W3040497714 hasConcept C17744445 @default.
- W3040497714 hasConcept C199539241 @default.
- W3040497714 hasConcept C2776359362 @default.
- W3040497714 hasConcept C28826006 @default.
- W3040497714 hasConcept C33923547 @default.
- W3040497714 hasConcept C41008148 @default.
- W3040497714 hasConcept C54907487 @default.
- W3040497714 hasConcept C74193536 @default.
- W3040497714 hasConcept C94625758 @default.
- W3040497714 hasConcept C98763669 @default.
- W3040497714 hasConceptScore W3040497714C105795698 @default.
- W3040497714 hasConceptScore W3040497714C106189395 @default.
- W3040497714 hasConceptScore W3040497714C106666656 @default.
- W3040497714 hasConceptScore W3040497714C114614502 @default.
- W3040497714 hasConceptScore W3040497714C119857082 @default.
- W3040497714 hasConceptScore W3040497714C126255220 @default.
- W3040497714 hasConceptScore W3040497714C134306372 @default.
- W3040497714 hasConceptScore W3040497714C14646407 @default.
- W3040497714 hasConceptScore W3040497714C158946198 @default.
- W3040497714 hasConceptScore W3040497714C159886148 @default.
- W3040497714 hasConceptScore W3040497714C163836022 @default.
- W3040497714 hasConceptScore W3040497714C17744445 @default.
- W3040497714 hasConceptScore W3040497714C199539241 @default.
- W3040497714 hasConceptScore W3040497714C2776359362 @default.
- W3040497714 hasConceptScore W3040497714C28826006 @default.
- W3040497714 hasConceptScore W3040497714C33923547 @default.
- W3040497714 hasConceptScore W3040497714C41008148 @default.
- W3040497714 hasConceptScore W3040497714C54907487 @default.
- W3040497714 hasConceptScore W3040497714C74193536 @default.
- W3040497714 hasConceptScore W3040497714C94625758 @default.
- W3040497714 hasConceptScore W3040497714C98763669 @default.
- W3040497714 hasLocation W30404977141 @default.
- W3040497714 hasLocation W30404977142 @default.
- W3040497714 hasOpenAccess W3040497714 @default.
- W3040497714 hasPrimaryLocation W30404977141 @default.
- W3040497714 hasRelatedWork W2191283 @default.
- W3040497714 hasRelatedWork W4776762 @default.
- W3040497714 hasRelatedWork W5133103 @default.
- W3040497714 hasRelatedWork W5657644 @default.
- W3040497714 hasRelatedWork W5718419 @default.
- W3040497714 hasRelatedWork W5876636 @default.
- W3040497714 hasRelatedWork W6516488 @default.
- W3040497714 hasRelatedWork W7424046 @default.
- W3040497714 hasRelatedWork W7769338 @default.
- W3040497714 hasRelatedWork W8709591 @default.
- W3040497714 isParatext "false" @default.
- W3040497714 isRetracted "false" @default.
- W3040497714 magId "3040497714" @default.
- W3040497714 workType "article" @default.