Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890960750> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2890960750 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 paper, 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.
- W2890960750 created "2018-09-27" @default.
- W2890960750 creator A5003753658 @default.
- W2890960750 creator A5035966558 @default.
- W2890960750 creator A5072744508 @default.
- W2890960750 date "2018-09-14" @default.
- W2890960750 modified "2023-10-03" @default.
- W2890960750 title "Dueling Bandits with Qualitative Feedback" @default.
- W2890960750 cites W1530210183 @default.
- W2890960750 cites W1553636730 @default.
- W2890960750 cites W1909146639 @default.
- W2890960750 cites W1972789308 @default.
- W2890960750 cites W1983962754 @default.
- W2890960750 cites W1988645907 @default.
- W2890960750 cites W2039522160 @default.
- W2890960750 cites W2044493620 @default.
- W2890960750 cites W2045097767 @default.
- W2890960750 cites W2555426513 @default.
- W2890960750 cites W2953193236 @default.
- W2890960750 cites W2962684386 @default.
- W2890960750 cites W2963912524 @default.
- W2890960750 doi "https://doi.org/10.48550/arxiv.1809.05274" @default.
- W2890960750 hasPublicationYear "2018" @default.
- W2890960750 type Work @default.
- W2890960750 sameAs 2890960750 @default.
- W2890960750 citedByCount "0" @default.
- W2890960750 crossrefType "posted-content" @default.
- W2890960750 hasAuthorship W2890960750A5003753658 @default.
- W2890960750 hasAuthorship W2890960750A5035966558 @default.
- W2890960750 hasAuthorship W2890960750A5072744508 @default.
- W2890960750 hasBestOaLocation W28909607501 @default.
- W2890960750 hasConcept C111335779 @default.
- W2890960750 hasConcept C11413529 @default.
- W2890960750 hasConcept C119857082 @default.
- W2890960750 hasConcept C126255220 @default.
- W2890960750 hasConcept C144024400 @default.
- W2890960750 hasConcept C154945302 @default.
- W2890960750 hasConcept C190248442 @default.
- W2890960750 hasConcept C2524010 @default.
- W2890960750 hasConcept C3018587665 @default.
- W2890960750 hasConcept C33923547 @default.
- W2890960750 hasConcept C36289849 @default.
- W2890960750 hasConcept C41008148 @default.
- W2890960750 hasConcept C50817715 @default.
- W2890960750 hasConceptScore W2890960750C111335779 @default.
- W2890960750 hasConceptScore W2890960750C11413529 @default.
- W2890960750 hasConceptScore W2890960750C119857082 @default.
- W2890960750 hasConceptScore W2890960750C126255220 @default.
- W2890960750 hasConceptScore W2890960750C144024400 @default.
- W2890960750 hasConceptScore W2890960750C154945302 @default.
- W2890960750 hasConceptScore W2890960750C190248442 @default.
- W2890960750 hasConceptScore W2890960750C2524010 @default.
- W2890960750 hasConceptScore W2890960750C3018587665 @default.
- W2890960750 hasConceptScore W2890960750C33923547 @default.
- W2890960750 hasConceptScore W2890960750C36289849 @default.
- W2890960750 hasConceptScore W2890960750C41008148 @default.
- W2890960750 hasConceptScore W2890960750C50817715 @default.
- W2890960750 hasLocation W28909607501 @default.
- W2890960750 hasLocation W28909607502 @default.
- W2890960750 hasOpenAccess W2890960750 @default.
- W2890960750 hasPrimaryLocation W28909607501 @default.
- W2890960750 hasRelatedWork W1954007105 @default.
- W2890960750 hasRelatedWork W2046840684 @default.
- W2890960750 hasRelatedWork W2301027479 @default.
- W2890960750 hasRelatedWork W2352590024 @default.
- W2890960750 hasRelatedWork W2742141334 @default.
- W2890960750 hasRelatedWork W3111617249 @default.
- W2890960750 hasRelatedWork W3159392088 @default.
- W2890960750 hasRelatedWork W3176362036 @default.
- W2890960750 hasRelatedWork W4287555357 @default.
- W2890960750 hasRelatedWork W4287634665 @default.
- W2890960750 isParatext "false" @default.
- W2890960750 isRetracted "false" @default.
- W2890960750 magId "2890960750" @default.
- W2890960750 workType "article" @default.