Matches in SemOpenAlex for { <https://semopenalex.org/work/W2605090753> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2605090753 abstract "Existing approaches to the multi-armed bandit (MAB) primarily rely on perfect recall of past actions to generate estimates for arm payoff probabilities; it is further assumed that the decision maker knows whether arm payoff probabilities can change. To capture the computational limitations many decision making systems face, we explore performance under bounded resources in the form of imperfect recall of past information. We present a finite memory automaton (FMA) designed to solve static and dynamic MAB problems. The FMA demonstrates that an agent can learn a low regret strategy without knowing whether arm payoff probabilities are static or dynamic and without having perfect recall of past actions. Roughly speaking, the automaton works by maintaining a relative ranking of arms rather than estimating precise payoff probabilities." @default.
- W2605090753 created "2017-04-14" @default.
- W2605090753 creator A5011795884 @default.
- W2605090753 date "2017-02-12" @default.
- W2605090753 modified "2023-09-26" @default.
- W2605090753 title "A Finite Memory Automaton for Two-Armed Bernoulli Bandit Problems" @default.
- W2605090753 doi "https://doi.org/10.1609/aaai.v31i1.11115" @default.
- W2605090753 hasPublicationYear "2017" @default.
- W2605090753 type Work @default.
- W2605090753 sameAs 2605090753 @default.
- W2605090753 citedByCount "0" @default.
- W2605090753 crossrefType "journal-article" @default.
- W2605090753 hasAuthorship W2605090753A5011795884 @default.
- W2605090753 hasBestOaLocation W26050907531 @default.
- W2605090753 hasConcept C112505250 @default.
- W2605090753 hasConcept C119857082 @default.
- W2605090753 hasConcept C123676819 @default.
- W2605090753 hasConcept C126255220 @default.
- W2605090753 hasConcept C127413603 @default.
- W2605090753 hasConcept C134306372 @default.
- W2605090753 hasConcept C138885662 @default.
- W2605090753 hasConcept C144237770 @default.
- W2605090753 hasConcept C146978453 @default.
- W2605090753 hasConcept C152361515 @default.
- W2605090753 hasConcept C154945302 @default.
- W2605090753 hasConcept C167729594 @default.
- W2605090753 hasConcept C189430467 @default.
- W2605090753 hasConcept C22171661 @default.
- W2605090753 hasConcept C2524010 @default.
- W2605090753 hasConcept C2780310539 @default.
- W2605090753 hasConcept C33923547 @default.
- W2605090753 hasConcept C34388435 @default.
- W2605090753 hasConcept C41008148 @default.
- W2605090753 hasConcept C41895202 @default.
- W2605090753 hasConcept C50817715 @default.
- W2605090753 hasConcept C80444323 @default.
- W2605090753 hasConceptScore W2605090753C112505250 @default.
- W2605090753 hasConceptScore W2605090753C119857082 @default.
- W2605090753 hasConceptScore W2605090753C123676819 @default.
- W2605090753 hasConceptScore W2605090753C126255220 @default.
- W2605090753 hasConceptScore W2605090753C127413603 @default.
- W2605090753 hasConceptScore W2605090753C134306372 @default.
- W2605090753 hasConceptScore W2605090753C138885662 @default.
- W2605090753 hasConceptScore W2605090753C144237770 @default.
- W2605090753 hasConceptScore W2605090753C146978453 @default.
- W2605090753 hasConceptScore W2605090753C152361515 @default.
- W2605090753 hasConceptScore W2605090753C154945302 @default.
- W2605090753 hasConceptScore W2605090753C167729594 @default.
- W2605090753 hasConceptScore W2605090753C189430467 @default.
- W2605090753 hasConceptScore W2605090753C22171661 @default.
- W2605090753 hasConceptScore W2605090753C2524010 @default.
- W2605090753 hasConceptScore W2605090753C2780310539 @default.
- W2605090753 hasConceptScore W2605090753C33923547 @default.
- W2605090753 hasConceptScore W2605090753C34388435 @default.
- W2605090753 hasConceptScore W2605090753C41008148 @default.
- W2605090753 hasConceptScore W2605090753C41895202 @default.
- W2605090753 hasConceptScore W2605090753C50817715 @default.
- W2605090753 hasConceptScore W2605090753C80444323 @default.
- W2605090753 hasIssue "1" @default.
- W2605090753 hasLocation W26050907531 @default.
- W2605090753 hasOpenAccess W2605090753 @default.
- W2605090753 hasPrimaryLocation W26050907531 @default.
- W2605090753 hasRelatedWork W1538636918 @default.
- W2605090753 hasRelatedWork W1575254328 @default.
- W2605090753 hasRelatedWork W1736541683 @default.
- W2605090753 hasRelatedWork W2126182393 @default.
- W2605090753 hasRelatedWork W2136794369 @default.
- W2605090753 hasRelatedWork W2161804242 @default.
- W2605090753 hasRelatedWork W2897387657 @default.
- W2605090753 hasRelatedWork W3122061151 @default.
- W2605090753 hasRelatedWork W3123366242 @default.
- W2605090753 hasRelatedWork W937639825 @default.
- W2605090753 hasVolume "31" @default.
- W2605090753 isParatext "false" @default.
- W2605090753 isRetracted "false" @default.
- W2605090753 magId "2605090753" @default.
- W2605090753 workType "article" @default.