Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367016730> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4367016730 endingPage "8" @default.
- W4367016730 startingPage "1" @default.
- W4367016730 abstract "The Bellman operator constitutes the foundation of dynamic programming (DP). An alternative is presented by the Gauss-Seidel operator, whose evaluation, differently from that of the Bellman operator where the states are all processed at once, updates one state at a time, while incorporating into the computation the interim results. The provably better convergence rate of DP methods based on the Gauss-Seidel operator comes at the price of an inherent sequentiality, which prevents the exploitation of modern multi-core systems. In this work we propose a new operator for dynamic programming, namely, the <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>mini-batch Bellman operator</i> , which aims at realizing the trade-off between the better convergence rate of the methods based on the Gauss-Seidel operator and the parallelization capability offered by the Bellman operator. After the introduction of the new operator, a theoretical analysis for validating its fundamental properties is conducted. Such properties allow one to successfully deploy the new operator in the main dynamic programming schemes, such as value iteration and modified policy iteration. We compare the convergence of the DP algorithm based on the new operator with its earlier counterparts, shedding light on the algorithmic advantages of the new formulation and the impact of the batch-size parameter on the convergence. Finally, an extensive numerical evaluation of the newly introduced operator is conducted. In accordance with the theoretical derivations, the numerical results show the competitive performance of the proposed operator and its superior flexibility, which allows one to adapt the efficiency of its iterations to different structures of MDPs and hardware setups." @default.
- W4367016730 created "2023-04-27" @default.
- W4367016730 creator A5007359599 @default.
- W4367016730 creator A5011462733 @default.
- W4367016730 creator A5086798183 @default.
- W4367016730 creator A5091908459 @default.
- W4367016730 date "2023-01-01" @default.
- W4367016730 modified "2023-09-30" @default.
- W4367016730 title "Parallel and Flexible Dynamic Programming Via the Mini-Batch Bellman Operator" @default.
- W4367016730 doi "https://doi.org/10.1109/tac.2023.3270060" @default.
- W4367016730 hasPublicationYear "2023" @default.
- W4367016730 type Work @default.
- W4367016730 citedByCount "0" @default.
- W4367016730 crossrefType "journal-article" @default.
- W4367016730 hasAuthorship W4367016730A5007359599 @default.
- W4367016730 hasAuthorship W4367016730A5011462733 @default.
- W4367016730 hasAuthorship W4367016730A5086798183 @default.
- W4367016730 hasAuthorship W4367016730A5091908459 @default.
- W4367016730 hasConcept C104317684 @default.
- W4367016730 hasConcept C11413529 @default.
- W4367016730 hasConcept C126255220 @default.
- W4367016730 hasConcept C158448853 @default.
- W4367016730 hasConcept C162324750 @default.
- W4367016730 hasConcept C17020691 @default.
- W4367016730 hasConcept C185592680 @default.
- W4367016730 hasConcept C26517878 @default.
- W4367016730 hasConcept C2777303404 @default.
- W4367016730 hasConcept C33923547 @default.
- W4367016730 hasConcept C37404715 @default.
- W4367016730 hasConcept C38652104 @default.
- W4367016730 hasConcept C41008148 @default.
- W4367016730 hasConcept C45374587 @default.
- W4367016730 hasConcept C50522688 @default.
- W4367016730 hasConcept C55493867 @default.
- W4367016730 hasConcept C57869625 @default.
- W4367016730 hasConcept C86339819 @default.
- W4367016730 hasConceptScore W4367016730C104317684 @default.
- W4367016730 hasConceptScore W4367016730C11413529 @default.
- W4367016730 hasConceptScore W4367016730C126255220 @default.
- W4367016730 hasConceptScore W4367016730C158448853 @default.
- W4367016730 hasConceptScore W4367016730C162324750 @default.
- W4367016730 hasConceptScore W4367016730C17020691 @default.
- W4367016730 hasConceptScore W4367016730C185592680 @default.
- W4367016730 hasConceptScore W4367016730C26517878 @default.
- W4367016730 hasConceptScore W4367016730C2777303404 @default.
- W4367016730 hasConceptScore W4367016730C33923547 @default.
- W4367016730 hasConceptScore W4367016730C37404715 @default.
- W4367016730 hasConceptScore W4367016730C38652104 @default.
- W4367016730 hasConceptScore W4367016730C41008148 @default.
- W4367016730 hasConceptScore W4367016730C45374587 @default.
- W4367016730 hasConceptScore W4367016730C50522688 @default.
- W4367016730 hasConceptScore W4367016730C55493867 @default.
- W4367016730 hasConceptScore W4367016730C57869625 @default.
- W4367016730 hasConceptScore W4367016730C86339819 @default.
- W4367016730 hasLocation W43670167301 @default.
- W4367016730 hasOpenAccess W4367016730 @default.
- W4367016730 hasPrimaryLocation W43670167301 @default.
- W4367016730 hasRelatedWork W2009191060 @default.
- W4367016730 hasRelatedWork W2038766029 @default.
- W4367016730 hasRelatedWork W2041508386 @default.
- W4367016730 hasRelatedWork W2042763317 @default.
- W4367016730 hasRelatedWork W2113250618 @default.
- W4367016730 hasRelatedWork W2389459180 @default.
- W4367016730 hasRelatedWork W2540751784 @default.
- W4367016730 hasRelatedWork W2908009812 @default.
- W4367016730 hasRelatedWork W4295922964 @default.
- W4367016730 hasRelatedWork W807645590 @default.
- W4367016730 isParatext "false" @default.
- W4367016730 isRetracted "false" @default.
- W4367016730 workType "article" @default.