Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951763655> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2951763655 endingPage "5556" @default.
- W2951763655 startingPage "5549" @default.
- W2951763655 abstract "We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the dueling bandit (DB) problem where the duel is carried out by comparing the qualitative feedback. Although we can naively use classic DB algorithms for solving the QDB problem, this reduction significantly worsens the performance—actually, in the QDB problem, the probability that one arm wins the duel over another arm can be directly estimated without carrying out actual duels. In this paper1, we propose such direct algorithms for the QDB problem. Our theoretical analysis shows that the proposed algorithms significantly outperform DB algorithms by incorporating the qualitative feedback, and experimental results also demonstrate vast improvement over the existing DB algorithms." @default.
- W2951763655 created "2019-06-27" @default.
- W2951763655 creator A5003753658 @default.
- W2951763655 creator A5035966558 @default.
- W2951763655 creator A5072744508 @default.
- W2951763655 date "2019-07-17" @default.
- W2951763655 modified "2023-10-16" @default.
- W2951763655 title "Dueling Bandits with Qualitative Feedback" @default.
- W2951763655 doi "https://doi.org/10.1609/aaai.v33i01.33015549" @default.
- W2951763655 hasPublicationYear "2019" @default.
- W2951763655 type Work @default.
- W2951763655 sameAs 2951763655 @default.
- W2951763655 citedByCount "4" @default.
- W2951763655 countsByYear W29517636552018 @default.
- W2951763655 countsByYear W29517636552020 @default.
- W2951763655 countsByYear W29517636552021 @default.
- W2951763655 crossrefType "journal-article" @default.
- W2951763655 hasAuthorship W2951763655A5003753658 @default.
- W2951763655 hasAuthorship W2951763655A5035966558 @default.
- W2951763655 hasAuthorship W2951763655A5072744508 @default.
- W2951763655 hasBestOaLocation W29517636551 @default.
- W2951763655 hasConcept C111335779 @default.
- W2951763655 hasConcept C11413529 @default.
- W2951763655 hasConcept C119857082 @default.
- W2951763655 hasConcept C126255220 @default.
- W2951763655 hasConcept C144024400 @default.
- W2951763655 hasConcept C154945302 @default.
- W2951763655 hasConcept C190248442 @default.
- W2951763655 hasConcept C2524010 @default.
- W2951763655 hasConcept C3018587665 @default.
- W2951763655 hasConcept C33923547 @default.
- W2951763655 hasConcept C36289849 @default.
- W2951763655 hasConcept C41008148 @default.
- W2951763655 hasConcept C50817715 @default.
- W2951763655 hasConceptScore W2951763655C111335779 @default.
- W2951763655 hasConceptScore W2951763655C11413529 @default.
- W2951763655 hasConceptScore W2951763655C119857082 @default.
- W2951763655 hasConceptScore W2951763655C126255220 @default.
- W2951763655 hasConceptScore W2951763655C144024400 @default.
- W2951763655 hasConceptScore W2951763655C154945302 @default.
- W2951763655 hasConceptScore W2951763655C190248442 @default.
- W2951763655 hasConceptScore W2951763655C2524010 @default.
- W2951763655 hasConceptScore W2951763655C3018587665 @default.
- W2951763655 hasConceptScore W2951763655C33923547 @default.
- W2951763655 hasConceptScore W2951763655C36289849 @default.
- W2951763655 hasConceptScore W2951763655C41008148 @default.
- W2951763655 hasConceptScore W2951763655C50817715 @default.
- W2951763655 hasIssue "01" @default.
- W2951763655 hasLocation W29517636551 @default.
- W2951763655 hasLocation W29517636552 @default.
- W2951763655 hasOpenAccess W2951763655 @default.
- W2951763655 hasPrimaryLocation W29517636551 @default.
- W2951763655 hasRelatedWork W1954007105 @default.
- W2951763655 hasRelatedWork W2046840684 @default.
- W2951763655 hasRelatedWork W2352590024 @default.
- W2951763655 hasRelatedWork W3006199854 @default.
- W2951763655 hasRelatedWork W3107474891 @default.
- W2951763655 hasRelatedWork W3111617249 @default.
- W2951763655 hasRelatedWork W3159392088 @default.
- W2951763655 hasRelatedWork W3176362036 @default.
- W2951763655 hasRelatedWork W4287555357 @default.
- W2951763655 hasRelatedWork W4287634665 @default.
- W2951763655 hasVolume "33" @default.
- W2951763655 isParatext "false" @default.
- W2951763655 isRetracted "false" @default.
- W2951763655 magId "2951763655" @default.
- W2951763655 workType "article" @default.