DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yun, Donggyu | ko |
dc.contributor.author | Ahn, Sumyeong | ko |
dc.contributor.author | Proutiere, Alexandre | ko |
dc.contributor.author | Shin, Jinwoo | ko |
dc.contributor.author | Yi, Yung | ko |
dc.date.accessioned | 2018-12-20T02:13:29Z | - |
dc.date.available | 2018-12-20T02:13:29Z | - |
dc.date.created | 2018-11-28 | - |
dc.date.created | 2018-11-28 | - |
dc.date.issued | 2018-06-18 | - |
dc.identifier.citation | 2018 ACM International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2018, pp.53 - 55 | - |
dc.identifier.uri | http://hdl.handle.net/10203/247468 | - |
dc.description.abstract | We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. We propose algorithms that are asymptotic-optimal and order-optimal in their regrets under the settings of stochastic and adversarial rewards, respectively. | - |
dc.language | English | - |
dc.publisher | Association for Computing Machinery, Inc | - |
dc.title | Multi-armed bandit with additional observations | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85052012891 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 53 | - |
dc.citation.endingpage | 55 | - |
dc.citation.publicationname | 2018 ACM International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS 2018 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Irvine, California | - |
dc.identifier.doi | 10.1145/3219617.3219639 | - |
dc.contributor.localauthor | Yun, Donggyu | - |
dc.contributor.nonIdAuthor | Ahn, Sumyeong | - |
dc.contributor.nonIdAuthor | Proutiere, Alexandre | - |
dc.contributor.nonIdAuthor | Shin, Jinwoo | - |
dc.contributor.nonIdAuthor | Yi, Yung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.