Matches in SemOpenAlex for { <https://semopenalex.org/work/W3020735350> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W3020735350 abstract "Upper confidence bound multi-armed bandit algorithms (UCB) typically rely on concentration in- equalities (such as Hoeffding’s inequality) for the creation of the upper confidence bound. Intu- itively, the tighter the bound is, the more likely the respective arm is or isn’t judged appropriately for selection. Hence we derive and utilise an optimal inequality. Usually the sample mean (and sometimes the sample variance) of previous rewards are the information which are used in the bounds which drive the algorithm, but intuitively the more infor- mation that taken from the previous rewards, the tighter the bound could be. Hence our inequality explicitly considers the values of each and every past reward into the upper bound expression which drives the method. We show how this UCB method fits into the broader scope of other information theoretic UCB algorithms, but unlike them is free from assumptions about the distribution of the data, We conclude by reporting some already established regret information, and give some numerical simulations to demonstrate the method’s effectiveness." @default.
- W3020735350 created "2020-05-01" @default.
- W3020735350 creator A5006462774 @default.
- W3020735350 date "2020-04-24" @default.
- W3020735350 modified "2023-10-17" @default.
- W3020735350 title "UCB with An Optimal Inequality" @default.
- W3020735350 cites W1992068214 @default.
- W3020735350 cites W2103012681 @default.
- W3020735350 cites W2116855184 @default.
- W3020735350 cites W2164530213 @default.
- W3020735350 cites W2168405694 @default.
- W3020735350 cites W2802546834 @default.
- W3020735350 cites W2949395086 @default.
- W3020735350 doi "https://doi.org/10.20944/preprints202004.0426.v1" @default.
- W3020735350 hasPublicationYear "2020" @default.
- W3020735350 type Work @default.
- W3020735350 sameAs 3020735350 @default.
- W3020735350 citedByCount "0" @default.
- W3020735350 crossrefType "posted-content" @default.
- W3020735350 hasAuthorship W3020735350A5006462774 @default.
- W3020735350 hasBestOaLocation W30207353501 @default.
- W3020735350 hasConcept C105795698 @default.
- W3020735350 hasConcept C110121322 @default.
- W3020735350 hasConcept C121955636 @default.
- W3020735350 hasConcept C126255220 @default.
- W3020735350 hasConcept C129848803 @default.
- W3020735350 hasConcept C134306372 @default.
- W3020735350 hasConcept C144237770 @default.
- W3020735350 hasConcept C149782125 @default.
- W3020735350 hasConcept C162324750 @default.
- W3020735350 hasConcept C185592680 @default.
- W3020735350 hasConcept C196083921 @default.
- W3020735350 hasConcept C198531522 @default.
- W3020735350 hasConcept C199360897 @default.
- W3020735350 hasConcept C2778012447 @default.
- W3020735350 hasConcept C33923547 @default.
- W3020735350 hasConcept C41008148 @default.
- W3020735350 hasConcept C43617362 @default.
- W3020735350 hasConcept C45555294 @default.
- W3020735350 hasConcept C50817715 @default.
- W3020735350 hasConcept C77553402 @default.
- W3020735350 hasConceptScore W3020735350C105795698 @default.
- W3020735350 hasConceptScore W3020735350C110121322 @default.
- W3020735350 hasConceptScore W3020735350C121955636 @default.
- W3020735350 hasConceptScore W3020735350C126255220 @default.
- W3020735350 hasConceptScore W3020735350C129848803 @default.
- W3020735350 hasConceptScore W3020735350C134306372 @default.
- W3020735350 hasConceptScore W3020735350C144237770 @default.
- W3020735350 hasConceptScore W3020735350C149782125 @default.
- W3020735350 hasConceptScore W3020735350C162324750 @default.
- W3020735350 hasConceptScore W3020735350C185592680 @default.
- W3020735350 hasConceptScore W3020735350C196083921 @default.
- W3020735350 hasConceptScore W3020735350C198531522 @default.
- W3020735350 hasConceptScore W3020735350C199360897 @default.
- W3020735350 hasConceptScore W3020735350C2778012447 @default.
- W3020735350 hasConceptScore W3020735350C33923547 @default.
- W3020735350 hasConceptScore W3020735350C41008148 @default.
- W3020735350 hasConceptScore W3020735350C43617362 @default.
- W3020735350 hasConceptScore W3020735350C45555294 @default.
- W3020735350 hasConceptScore W3020735350C50817715 @default.
- W3020735350 hasConceptScore W3020735350C77553402 @default.
- W3020735350 hasLocation W30207353501 @default.
- W3020735350 hasOpenAccess W3020735350 @default.
- W3020735350 hasPrimaryLocation W30207353501 @default.
- W3020735350 hasRelatedWork W15463960 @default.
- W3020735350 hasRelatedWork W17066250 @default.
- W3020735350 hasRelatedWork W19344704 @default.
- W3020735350 hasRelatedWork W20268109 @default.
- W3020735350 hasRelatedWork W29685465 @default.
- W3020735350 hasRelatedWork W40762328 @default.
- W3020735350 hasRelatedWork W41355593 @default.
- W3020735350 hasRelatedWork W6021274 @default.
- W3020735350 hasRelatedWork W7316913 @default.
- W3020735350 hasRelatedWork W44488664 @default.
- W3020735350 isParatext "false" @default.
- W3020735350 isRetracted "false" @default.
- W3020735350 magId "3020735350" @default.
- W3020735350 workType "article" @default.