Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092771987> ?p ?o ?g. }
- W3092771987 abstract "We study a variant of the classical multi-armed bandit problem (MABP) which we call as Multi-Armed Bandits with dependent arms. More specifically, multiple arms are grouped together to form a cluster, and the reward distributions of arms belonging to the same cluster are known functions of an unknown parameter that is a characteristic of the cluster. Thus, pulling an arm $i$ not only reveals information about its own reward distribution, but also about all those arms that share the same cluster with arm $i$. This correlation amongst the arms complicates the exploration-exploitation trade-off that is encountered in the MABP because the observation dependencies allow us to test simultaneously multiple hypotheses regarding the optimality of an arm. We develop learning algorithms based on the UCB principle which utilize these additional side observations appropriately while performing exploration-exploitation trade-off. We show that the regret of our algorithms grows as $O(Klog T)$, where $K$ is the number of clusters. In contrast, for an algorithm such as the vanilla UCB that is optimal for the classical MABP and does not utilize these dependencies, the regret scales as $O(Mlog T)$ where $M$ is the number of arms." @default.
- W3092771987 created "2020-10-22" @default.
- W3092771987 creator A5003200620 @default.
- W3092771987 creator A5028757222 @default.
- W3092771987 creator A5035752536 @default.
- W3092771987 creator A5055489202 @default.
- W3092771987 date "2020-10-13" @default.
- W3092771987 modified "2023-09-27" @default.
- W3092771987 title "Multi-Armed Bandits with Dependent Arms." @default.
- W3092771987 cites W1487320471 @default.
- W3092771987 cites W1546851689 @default.
- W3092771987 cites W1594563152 @default.
- W3092771987 cites W1615542443 @default.
- W3092771987 cites W1822035899 @default.
- W3092771987 cites W1970930040 @default.
- W3092771987 cites W2009551863 @default.
- W3092771987 cites W2010189695 @default.
- W3092771987 cites W2012731843 @default.
- W3092771987 cites W2024440951 @default.
- W3092771987 cites W2049934117 @default.
- W3092771987 cites W2061753713 @default.
- W3092771987 cites W2093562354 @default.
- W3092771987 cites W2096382242 @default.
- W3092771987 cites W2099111195 @default.
- W3092771987 cites W2108114251 @default.
- W3092771987 cites W2112420033 @default.
- W3092771987 cites W2119738618 @default.
- W3092771987 cites W2119850747 @default.
- W3092771987 cites W2123838014 @default.
- W3092771987 cites W2129301967 @default.
- W3092771987 cites W2158807713 @default.
- W3092771987 cites W2167555642 @default.
- W3092771987 cites W2317700292 @default.
- W3092771987 cites W2341171179 @default.
- W3092771987 cites W2890134435 @default.
- W3092771987 cites W2896487759 @default.
- W3092771987 cites W2963389158 @default.
- W3092771987 cites W2963465244 @default.
- W3092771987 cites W2963511480 @default.
- W3092771987 cites W2963568654 @default.
- W3092771987 cites W2963850079 @default.
- W3092771987 cites W2989972589 @default.
- W3092771987 cites W3016156492 @default.
- W3092771987 cites W3030192008 @default.
- W3092771987 cites W3033901130 @default.
- W3092771987 hasPublicationYear "2020" @default.
- W3092771987 type Work @default.
- W3092771987 sameAs 3092771987 @default.
- W3092771987 citedByCount "2" @default.
- W3092771987 countsByYear W30927719872021 @default.
- W3092771987 crossrefType "posted-content" @default.
- W3092771987 hasAuthorship W3092771987A5003200620 @default.
- W3092771987 hasAuthorship W3092771987A5028757222 @default.
- W3092771987 hasAuthorship W3092771987A5035752536 @default.
- W3092771987 hasAuthorship W3092771987A5055489202 @default.
- W3092771987 hasConcept C110121322 @default.
- W3092771987 hasConcept C11413529 @default.
- W3092771987 hasConcept C119857082 @default.
- W3092771987 hasConcept C126255220 @default.
- W3092771987 hasConcept C134306372 @default.
- W3092771987 hasConcept C154945302 @default.
- W3092771987 hasConcept C164866538 @default.
- W3092771987 hasConcept C199360897 @default.
- W3092771987 hasConcept C2776502983 @default.
- W3092771987 hasConcept C33923547 @default.
- W3092771987 hasConcept C41008148 @default.
- W3092771987 hasConcept C50817715 @default.
- W3092771987 hasConceptScore W3092771987C110121322 @default.
- W3092771987 hasConceptScore W3092771987C11413529 @default.
- W3092771987 hasConceptScore W3092771987C119857082 @default.
- W3092771987 hasConceptScore W3092771987C126255220 @default.
- W3092771987 hasConceptScore W3092771987C134306372 @default.
- W3092771987 hasConceptScore W3092771987C154945302 @default.
- W3092771987 hasConceptScore W3092771987C164866538 @default.
- W3092771987 hasConceptScore W3092771987C199360897 @default.
- W3092771987 hasConceptScore W3092771987C2776502983 @default.
- W3092771987 hasConceptScore W3092771987C33923547 @default.
- W3092771987 hasConceptScore W3092771987C41008148 @default.
- W3092771987 hasConceptScore W3092771987C50817715 @default.
- W3092771987 hasLocation W30927719871 @default.
- W3092771987 hasOpenAccess W3092771987 @default.
- W3092771987 hasPrimaryLocation W30927719871 @default.
- W3092771987 hasRelatedWork W1553290137 @default.
- W3092771987 hasRelatedWork W18595695 @default.
- W3092771987 hasRelatedWork W1977989560 @default.
- W3092771987 hasRelatedWork W2167555642 @default.
- W3092771987 hasRelatedWork W2185823609 @default.
- W3092771987 hasRelatedWork W2202218714 @default.
- W3092771987 hasRelatedWork W2728499956 @default.
- W3092771987 hasRelatedWork W2788664414 @default.
- W3092771987 hasRelatedWork W2796393948 @default.
- W3092771987 hasRelatedWork W2886535806 @default.
- W3092771987 hasRelatedWork W2910458483 @default.
- W3092771987 hasRelatedWork W2913787888 @default.
- W3092771987 hasRelatedWork W2914049206 @default.
- W3092771987 hasRelatedWork W2952853722 @default.
- W3092771987 hasRelatedWork W3006831017 @default.
- W3092771987 hasRelatedWork W3009708787 @default.
- W3092771987 hasRelatedWork W3102508570 @default.
- W3092771987 hasRelatedWork W3135553473 @default.