Matches in SemOpenAlex for { <https://semopenalex.org/work/W79689364> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W79689364 endingPage "630" @default.
- W79689364 startingPage "624" @default.
- W79689364 abstract "Exploitation-oriented learning (XoL) is a novel approach to goal-directed learning from interaction. Reinforcement learning is much more focused on learning and ensures optimality in Markov decision process (MDP) environments, XoL involves learning a rational policy that obtains rewards continuously and very quickly. PS-r * , a form of XoL, involves learning a useful rational policy not inferior to the random walk in the partially observed Markov decision process (POMDP) where reward types number one. PS-r * , however, requires O(MN 2 ) memory where N is the number of sensory input types and M is an action. We propose PS-r # for learning a useful rational policy in the POMDP using O(MN) memory. PS-r # effectiveness is confirmed in numerical examples." @default.
- W79689364 created "2016-06-24" @default.
- W79689364 creator A5062124983 @default.
- W79689364 creator A5083317982 @default.
- W79689364 date "2009-11-20" @default.
- W79689364 modified "2023-09-29" @default.
- W79689364 title "Exploitation-Oriented Learning PS-r<sup>#</sup>" @default.
- W79689364 cites W1485905671 @default.
- W79689364 cites W150470534 @default.
- W79689364 cites W1541084404 @default.
- W79689364 cites W1570690983 @default.
- W79689364 cites W1918052378 @default.
- W79689364 cites W1996625075 @default.
- W79689364 cites W2119717200 @default.
- W79689364 cites W2136736007 @default.
- W79689364 cites W301163710 @default.
- W79689364 cites W4214717370 @default.
- W79689364 doi "https://doi.org/10.20965/jaciii.2009.p0624" @default.
- W79689364 hasPublicationYear "2009" @default.
- W79689364 type Work @default.
- W79689364 sameAs 79689364 @default.
- W79689364 citedByCount "28" @default.
- W79689364 countsByYear W796893642012 @default.
- W79689364 countsByYear W796893642013 @default.
- W79689364 countsByYear W796893642014 @default.
- W79689364 countsByYear W796893642015 @default.
- W79689364 countsByYear W796893642016 @default.
- W79689364 countsByYear W796893642017 @default.
- W79689364 countsByYear W796893642018 @default.
- W79689364 countsByYear W796893642019 @default.
- W79689364 countsByYear W796893642021 @default.
- W79689364 countsByYear W796893642022 @default.
- W79689364 crossrefType "journal-article" @default.
- W79689364 hasAuthorship W79689364A5062124983 @default.
- W79689364 hasAuthorship W79689364A5083317982 @default.
- W79689364 hasBestOaLocation W796893641 @default.
- W79689364 hasConcept C105795698 @default.
- W79689364 hasConcept C106189395 @default.
- W79689364 hasConcept C119857082 @default.
- W79689364 hasConcept C121332964 @default.
- W79689364 hasConcept C126255220 @default.
- W79689364 hasConcept C154945302 @default.
- W79689364 hasConcept C159886148 @default.
- W79689364 hasConcept C163836022 @default.
- W79689364 hasConcept C17098449 @default.
- W79689364 hasConcept C188116033 @default.
- W79689364 hasConcept C199360897 @default.
- W79689364 hasConcept C2780791683 @default.
- W79689364 hasConcept C33923547 @default.
- W79689364 hasConcept C41008148 @default.
- W79689364 hasConcept C62520636 @default.
- W79689364 hasConcept C97541855 @default.
- W79689364 hasConcept C98045186 @default.
- W79689364 hasConcept C98763669 @default.
- W79689364 hasConceptScore W79689364C105795698 @default.
- W79689364 hasConceptScore W79689364C106189395 @default.
- W79689364 hasConceptScore W79689364C119857082 @default.
- W79689364 hasConceptScore W79689364C121332964 @default.
- W79689364 hasConceptScore W79689364C126255220 @default.
- W79689364 hasConceptScore W79689364C154945302 @default.
- W79689364 hasConceptScore W79689364C159886148 @default.
- W79689364 hasConceptScore W79689364C163836022 @default.
- W79689364 hasConceptScore W79689364C17098449 @default.
- W79689364 hasConceptScore W79689364C188116033 @default.
- W79689364 hasConceptScore W79689364C199360897 @default.
- W79689364 hasConceptScore W79689364C2780791683 @default.
- W79689364 hasConceptScore W79689364C33923547 @default.
- W79689364 hasConceptScore W79689364C41008148 @default.
- W79689364 hasConceptScore W79689364C62520636 @default.
- W79689364 hasConceptScore W79689364C97541855 @default.
- W79689364 hasConceptScore W79689364C98045186 @default.
- W79689364 hasConceptScore W79689364C98763669 @default.
- W79689364 hasIssue "6" @default.
- W79689364 hasLocation W796893641 @default.
- W79689364 hasOpenAccess W79689364 @default.
- W79689364 hasPrimaryLocation W796893641 @default.
- W79689364 hasRelatedWork W1515117609 @default.
- W79689364 hasRelatedWork W1536296381 @default.
- W79689364 hasRelatedWork W1663497315 @default.
- W79689364 hasRelatedWork W2123927904 @default.
- W79689364 hasRelatedWork W2124144580 @default.
- W79689364 hasRelatedWork W2146763310 @default.
- W79689364 hasRelatedWork W2156371714 @default.
- W79689364 hasRelatedWork W2347690758 @default.
- W79689364 hasRelatedWork W3167472281 @default.
- W79689364 hasRelatedWork W3211465897 @default.
- W79689364 hasVolume "13" @default.
- W79689364 isParatext "false" @default.
- W79689364 isRetracted "false" @default.
- W79689364 magId "79689364" @default.
- W79689364 workType "article" @default.