Matches in SemOpenAlex for { <https://semopenalex.org/work/W1761637522> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W1761637522 endingPage "1216" @default.
- W1761637522 startingPage "1211" @default.
- W1761637522 abstract "We introduce the budget-limited multi-armed bandit (MAB), which captures situations where a learner's actions are costly and constrained by a fixed budget that is incommensurable with the rewards earned from the bandit machine, and then describe a first algorithm for solving it. Since the learner has a budget, the problem's duration is finite. Consequently an optimal exploitation policy is not to pull the optimal arm repeatedly, but to pull the combination of arms that maximises the agent's total reward within the budget. As such, the rewards for all arms must be estimated, because any of them may appear in the optimal combination. This difference from existing MABs means that new approaches to maximising the total reward are required. To this end, we propose an ∊-first algorithm, in which the first ∊ of the budget is used solely to learn the arms' rewards (exploration), while the remaining 1 - ∊ is used to maximise the received reward based on those estimates (exploitation). We derive bounds on the algorithm's loss for generic and uniform exploration methods, and compare its performance with traditional MAB algorithms under various distributions of rewards and costs, showing that it outperforms the others by up to 50%." @default.
- W1761637522 created "2016-06-24" @default.
- W1761637522 creator A5041799105 @default.
- W1761637522 creator A5047020165 @default.
- W1761637522 creator A5064277708 @default.
- W1761637522 creator A5080848978 @default.
- W1761637522 creator A5085586757 @default.
- W1761637522 date "2010-07-11" @default.
- W1761637522 modified "2023-09-24" @default.
- W1761637522 title "ε-first policies for budget-limited multi-armed bandits" @default.
- W1761637522 cites W1587673378 @default.
- W1761637522 cites W1881419322 @default.
- W1761637522 cites W1998498767 @default.
- W1761637522 cites W2068637807 @default.
- W1761637522 cites W2084002770 @default.
- W1761637522 cites W2087203776 @default.
- W1761637522 cites W2124535870 @default.
- W1761637522 cites W2135664069 @default.
- W1761637522 cites W2168405694 @default.
- W1761637522 cites W3124379662 @default.
- W1761637522 hasPublicationYear "2010" @default.
- W1761637522 type Work @default.
- W1761637522 sameAs 1761637522 @default.
- W1761637522 citedByCount "38" @default.
- W1761637522 countsByYear W17616375222012 @default.
- W1761637522 countsByYear W17616375222013 @default.
- W1761637522 countsByYear W17616375222014 @default.
- W1761637522 countsByYear W17616375222015 @default.
- W1761637522 countsByYear W17616375222016 @default.
- W1761637522 countsByYear W17616375222017 @default.
- W1761637522 countsByYear W17616375222018 @default.
- W1761637522 countsByYear W17616375222019 @default.
- W1761637522 countsByYear W17616375222020 @default.
- W1761637522 countsByYear W17616375222021 @default.
- W1761637522 crossrefType "proceedings-article" @default.
- W1761637522 hasAuthorship W1761637522A5041799105 @default.
- W1761637522 hasAuthorship W1761637522A5047020165 @default.
- W1761637522 hasAuthorship W1761637522A5064277708 @default.
- W1761637522 hasAuthorship W1761637522A5080848978 @default.
- W1761637522 hasAuthorship W1761637522A5085586757 @default.
- W1761637522 hasConcept C112758219 @default.
- W1761637522 hasConcept C119857082 @default.
- W1761637522 hasConcept C123197309 @default.
- W1761637522 hasConcept C124952713 @default.
- W1761637522 hasConcept C126255220 @default.
- W1761637522 hasConcept C142362112 @default.
- W1761637522 hasConcept C162324750 @default.
- W1761637522 hasConcept C175444787 @default.
- W1761637522 hasConcept C33923547 @default.
- W1761637522 hasConcept C41008148 @default.
- W1761637522 hasConcept C42475967 @default.
- W1761637522 hasConcept C50817715 @default.
- W1761637522 hasConcept C8505890 @default.
- W1761637522 hasConceptScore W1761637522C112758219 @default.
- W1761637522 hasConceptScore W1761637522C119857082 @default.
- W1761637522 hasConceptScore W1761637522C123197309 @default.
- W1761637522 hasConceptScore W1761637522C124952713 @default.
- W1761637522 hasConceptScore W1761637522C126255220 @default.
- W1761637522 hasConceptScore W1761637522C142362112 @default.
- W1761637522 hasConceptScore W1761637522C162324750 @default.
- W1761637522 hasConceptScore W1761637522C175444787 @default.
- W1761637522 hasConceptScore W1761637522C33923547 @default.
- W1761637522 hasConceptScore W1761637522C41008148 @default.
- W1761637522 hasConceptScore W1761637522C42475967 @default.
- W1761637522 hasConceptScore W1761637522C50817715 @default.
- W1761637522 hasConceptScore W1761637522C8505890 @default.
- W1761637522 hasLocation W17616375221 @default.
- W1761637522 hasOpenAccess W1761637522 @default.
- W1761637522 hasPrimaryLocation W17616375221 @default.
- W1761637522 hasRelatedWork W1501823362 @default.
- W1761637522 hasRelatedWork W1553290137 @default.
- W1761637522 hasRelatedWork W1699297496 @default.
- W1761637522 hasRelatedWork W1881419322 @default.
- W1761637522 hasRelatedWork W1911551976 @default.
- W1761637522 hasRelatedWork W1998498767 @default.
- W1761637522 hasRelatedWork W2009551863 @default.
- W1761637522 hasRelatedWork W2039522160 @default.
- W1761637522 hasRelatedWork W2049934117 @default.
- W1761637522 hasRelatedWork W2077902449 @default.
- W1761637522 hasRelatedWork W2093562354 @default.
- W1761637522 hasRelatedWork W2093825590 @default.
- W1761637522 hasRelatedWork W2108114251 @default.
- W1761637522 hasRelatedWork W2110005947 @default.
- W1761637522 hasRelatedWork W2142971854 @default.
- W1761637522 hasRelatedWork W2167603139 @default.
- W1761637522 hasRelatedWork W2168405694 @default.
- W1761637522 hasRelatedWork W2400128071 @default.
- W1761637522 hasRelatedWork W2914156981 @default.
- W1761637522 hasRelatedWork W50486269 @default.
- W1761637522 isParatext "false" @default.
- W1761637522 isRetracted "false" @default.
- W1761637522 magId "1761637522" @default.
- W1761637522 workType "article" @default.