Matches in SemOpenAlex for { <https://semopenalex.org/work/W1739018506> ?p ?o ?g. }
- W1739018506 endingPage "1609" @default.
- W1739018506 startingPage "1601" @default.
- W1739018506 abstract "The conventional model for online planning under uncertainty assumes that an agent can stop and plan without incurring costs for the time spent planning. However, planning time is not free in most real-world settings. For example, an autonomous drone is subject to nature's forces, like gravity, even while it thinks, and must either pay a price for counteracting these forces to stay in place, or grapple with the state change caused by acquiescing to them. Policy optimization in these settings requires metareasoning-- a process that trades off the cost of planning and the potential policy improvement that can be achieved. We formalize and analyze the metareasoning problem for Markov Decision Processes (MDPs). Our work subsumes previously studied special cases of metareasoning and shows that in the general case, metareasoning is at most polynomially harder than solving MDPs with any given algorithm that disregards the cost of thinking. For reasons we discuss, optimal general metareasoning turns out to be impractical, motivating approximations. We present approximate metareasoning procedures which rely on special properties of the BRTDP planning algorithm and explore the effectiveness of our methods on a variety of problems." @default.
- W1739018506 created "2016-06-24" @default.
- W1739018506 creator A5014792235 @default.
- W1739018506 creator A5028114802 @default.
- W1739018506 creator A5043228682 @default.
- W1739018506 creator A5067758026 @default.
- W1739018506 date "2015-07-25" @default.
- W1739018506 modified "2023-09-26" @default.
- W1739018506 title "Metareasoning for planning under uncertainty" @default.
- W1739018506 cites W1484610779 @default.
- W1739018506 cites W1510924215 @default.
- W1739018506 cites W1515851193 @default.
- W1739018506 cites W1525110644 @default.
- W1739018506 cites W1576452626 @default.
- W1739018506 cites W1589640093 @default.
- W1739018506 cites W1625390266 @default.
- W1739018506 cites W17331372 @default.
- W1739018506 cites W1852295850 @default.
- W1739018506 cites W1976129448 @default.
- W1739018506 cites W1993711637 @default.
- W1739018506 cites W2009533501 @default.
- W1739018506 cites W2028145673 @default.
- W1739018506 cites W2040827706 @default.
- W1739018506 cites W2050880818 @default.
- W1739018506 cites W2096449640 @default.
- W1739018506 cites W2116708838 @default.
- W1739018506 cites W2148818117 @default.
- W1739018506 cites W2157720863 @default.
- W1739018506 cites W2170930374 @default.
- W1739018506 cites W2295152709 @default.
- W1739018506 cites W2404068774 @default.
- W1739018506 cites W2552833116 @default.
- W1739018506 cites W2962688548 @default.
- W1739018506 cites W75161650 @default.
- W1739018506 hasPublicationYear "2015" @default.
- W1739018506 type Work @default.
- W1739018506 sameAs 1739018506 @default.
- W1739018506 citedByCount "3" @default.
- W1739018506 countsByYear W17390185062015 @default.
- W1739018506 countsByYear W17390185062020 @default.
- W1739018506 countsByYear W17390185062021 @default.
- W1739018506 crossrefType "proceedings-article" @default.
- W1739018506 hasAuthorship W1739018506A5014792235 @default.
- W1739018506 hasAuthorship W1739018506A5028114802 @default.
- W1739018506 hasAuthorship W1739018506A5043228682 @default.
- W1739018506 hasAuthorship W1739018506A5067758026 @default.
- W1739018506 hasConcept C105795698 @default.
- W1739018506 hasConcept C106189395 @default.
- W1739018506 hasConcept C111919701 @default.
- W1739018506 hasConcept C114073186 @default.
- W1739018506 hasConcept C11413529 @default.
- W1739018506 hasConcept C119857082 @default.
- W1739018506 hasConcept C126255220 @default.
- W1739018506 hasConcept C127413603 @default.
- W1739018506 hasConcept C136197465 @default.
- W1739018506 hasConcept C154945302 @default.
- W1739018506 hasConcept C159886148 @default.
- W1739018506 hasConcept C163836022 @default.
- W1739018506 hasConcept C166957645 @default.
- W1739018506 hasConcept C17098449 @default.
- W1739018506 hasConcept C18762648 @default.
- W1739018506 hasConcept C2776505523 @default.
- W1739018506 hasConcept C33923547 @default.
- W1739018506 hasConcept C41008148 @default.
- W1739018506 hasConcept C42475967 @default.
- W1739018506 hasConcept C48103436 @default.
- W1739018506 hasConcept C78519656 @default.
- W1739018506 hasConcept C95457728 @default.
- W1739018506 hasConcept C98045186 @default.
- W1739018506 hasConcept C98763669 @default.
- W1739018506 hasConceptScore W1739018506C105795698 @default.
- W1739018506 hasConceptScore W1739018506C106189395 @default.
- W1739018506 hasConceptScore W1739018506C111919701 @default.
- W1739018506 hasConceptScore W1739018506C114073186 @default.
- W1739018506 hasConceptScore W1739018506C11413529 @default.
- W1739018506 hasConceptScore W1739018506C119857082 @default.
- W1739018506 hasConceptScore W1739018506C126255220 @default.
- W1739018506 hasConceptScore W1739018506C127413603 @default.
- W1739018506 hasConceptScore W1739018506C136197465 @default.
- W1739018506 hasConceptScore W1739018506C154945302 @default.
- W1739018506 hasConceptScore W1739018506C159886148 @default.
- W1739018506 hasConceptScore W1739018506C163836022 @default.
- W1739018506 hasConceptScore W1739018506C166957645 @default.
- W1739018506 hasConceptScore W1739018506C17098449 @default.
- W1739018506 hasConceptScore W1739018506C18762648 @default.
- W1739018506 hasConceptScore W1739018506C2776505523 @default.
- W1739018506 hasConceptScore W1739018506C33923547 @default.
- W1739018506 hasConceptScore W1739018506C41008148 @default.
- W1739018506 hasConceptScore W1739018506C42475967 @default.
- W1739018506 hasConceptScore W1739018506C48103436 @default.
- W1739018506 hasConceptScore W1739018506C78519656 @default.
- W1739018506 hasConceptScore W1739018506C95457728 @default.
- W1739018506 hasConceptScore W1739018506C98045186 @default.
- W1739018506 hasConceptScore W1739018506C98763669 @default.
- W1739018506 hasLocation W17390185061 @default.
- W1739018506 hasOpenAccess W1739018506 @default.
- W1739018506 hasPrimaryLocation W17390185061 @default.
- W1739018506 hasRelatedWork W1237749114 @default.