Matches in SemOpenAlex for { <https://semopenalex.org/work/W1553636730> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W1553636730 abstract "We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based on the information divergence. An algorithm that is inspired by the Deterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010) is proposed, and its regret is analyzed. The proposed algorithm is found to be the first one with a regret upper bound that matches the lower bound. Experimental comparisons of dueling bandit algorithms show that the proposed algorithm significantly outperforms existing ones." @default.
- W1553636730 created "2016-06-24" @default.
- W1553636730 creator A5003753658 @default.
- W1553636730 creator A5020912760 @default.
- W1553636730 creator A5031707680 @default.
- W1553636730 creator A5038978456 @default.
- W1553636730 date "2015-06-08" @default.
- W1553636730 modified "2023-10-03" @default.
- W1553636730 title "Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem" @default.
- W1553636730 cites W1501823362 @default.
- W1553636730 cites W1699297496 @default.
- W1553636730 cites W1973885534 @default.
- W1553636730 cites W2000080679 @default.
- W1553636730 cites W2007815473 @default.
- W1553636730 cites W2044493620 @default.
- W1553636730 cites W2168405694 @default.
- W1553636730 cites W2249408652 @default.
- W1553636730 cites W2951175152 @default.
- W1553636730 hasPublicationYear "2015" @default.
- W1553636730 type Work @default.
- W1553636730 sameAs 1553636730 @default.
- W1553636730 citedByCount "10" @default.
- W1553636730 countsByYear W15536367302016 @default.
- W1553636730 countsByYear W15536367302017 @default.
- W1553636730 countsByYear W15536367302018 @default.
- W1553636730 countsByYear W15536367302019 @default.
- W1553636730 crossrefType "posted-content" @default.
- W1553636730 hasAuthorship W1553636730A5003753658 @default.
- W1553636730 hasAuthorship W1553636730A5020912760 @default.
- W1553636730 hasAuthorship W1553636730A5031707680 @default.
- W1553636730 hasAuthorship W1553636730A5038978456 @default.
- W1553636730 hasConcept C105795698 @default.
- W1553636730 hasConcept C11413529 @default.
- W1553636730 hasConcept C121332964 @default.
- W1553636730 hasConcept C126255220 @default.
- W1553636730 hasConcept C134306372 @default.
- W1553636730 hasConcept C138885662 @default.
- W1553636730 hasConcept C207390915 @default.
- W1553636730 hasConcept C2778334786 @default.
- W1553636730 hasConcept C33923547 @default.
- W1553636730 hasConcept C41008148 @default.
- W1553636730 hasConcept C41895202 @default.
- W1553636730 hasConcept C44870925 @default.
- W1553636730 hasConcept C50817715 @default.
- W1553636730 hasConcept C77553402 @default.
- W1553636730 hasConceptScore W1553636730C105795698 @default.
- W1553636730 hasConceptScore W1553636730C11413529 @default.
- W1553636730 hasConceptScore W1553636730C121332964 @default.
- W1553636730 hasConceptScore W1553636730C126255220 @default.
- W1553636730 hasConceptScore W1553636730C134306372 @default.
- W1553636730 hasConceptScore W1553636730C138885662 @default.
- W1553636730 hasConceptScore W1553636730C207390915 @default.
- W1553636730 hasConceptScore W1553636730C2778334786 @default.
- W1553636730 hasConceptScore W1553636730C33923547 @default.
- W1553636730 hasConceptScore W1553636730C41008148 @default.
- W1553636730 hasConceptScore W1553636730C41895202 @default.
- W1553636730 hasConceptScore W1553636730C44870925 @default.
- W1553636730 hasConceptScore W1553636730C50817715 @default.
- W1553636730 hasConceptScore W1553636730C77553402 @default.
- W1553636730 hasLocation W15536367301 @default.
- W1553636730 hasOpenAccess W1553636730 @default.
- W1553636730 hasPrimaryLocation W15536367301 @default.
- W1553636730 hasRelatedWork W1518788040 @default.
- W1553636730 hasRelatedWork W1569127318 @default.
- W1553636730 hasRelatedWork W1847425745 @default.
- W1553636730 hasRelatedWork W1975779216 @default.
- W1553636730 hasRelatedWork W2044493620 @default.
- W1553636730 hasRelatedWork W2088253680 @default.
- W1553636730 hasRelatedWork W2120745256 @default.
- W1553636730 hasRelatedWork W2135053554 @default.
- W1553636730 hasRelatedWork W2185036126 @default.
- W1553636730 hasRelatedWork W2249408652 @default.
- W1553636730 hasRelatedWork W2346878437 @default.
- W1553636730 hasRelatedWork W2752599163 @default.
- W1553636730 hasRelatedWork W2768247474 @default.
- W1553636730 hasRelatedWork W2951092852 @default.
- W1553636730 hasRelatedWork W2953128025 @default.
- W1553636730 hasRelatedWork W2970893474 @default.
- W1553636730 hasRelatedWork W2972941693 @default.
- W1553636730 hasRelatedWork W2979645311 @default.
- W1553636730 hasRelatedWork W3202768707 @default.
- W1553636730 hasRelatedWork W50636094 @default.
- W1553636730 isParatext "false" @default.
- W1553636730 isRetracted "false" @default.
- W1553636730 magId "1553636730" @default.
- W1553636730 workType "article" @default.