FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048056964> ?p ?o ?g. }

• W3048056964 endingPage "8957" @default.
• W3048056964 startingPage "8950" @default.
• W3048056964 abstract "We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus on playing near-optimal arms. To this end, we suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some ε. We then present a variant of the Thompson Sampling (TS) algorithm, called ε-TS, and prove its asymptotic optimality in terms of the lenient regret. Importantly, we show that when the mean of the optimal arm is high enough, the lenient regret of ε-TS is bounded by a constant. Finally, we show that ε-TS can be applied to improve the performance when the agent knows a lower bound of the suboptimality gaps." @default.
• W3048056964 created "2020-08-13" @default.
• W3048056964 creator A5018784842 @default.
• W3048056964 creator A5036260775 @default.
• W3048056964 date "2021-05-18" @default.
• W3048056964 modified "2023-10-16" @default.
• W3048056964 title "Lenient Regret for Multi-Armed Bandits" @default.
• W3048056964 cites W107583932 @default.
• W3048056964 cites W1861050369 @default.
• W3048056964 cites W1911551976 @default.
• W3048056964 cites W1983962754 @default.
• W3048056964 cites W1998498767 @default.
• W3048056964 cites W2009551863 @default.
• W3048056964 cites W2039522160 @default.
• W3048056964 cites W2049934117 @default.
• W3048056964 cites W2099179721 @default.
• W3048056964 cites W2103405567 @default.
• W3048056964 cites W2108738385 @default.
• W3048056964 cites W2110632090 @default.
• W3048056964 cites W2121863487 @default.
• W3048056964 cites W2129301967 @default.
• W3048056964 cites W2132876566 @default.
• W3048056964 cites W2141645258 @default.
• W3048056964 cites W2158319693 @default.
• W3048056964 cites W2166253248 @default.
• W3048056964 cites W2168405694 @default.
• W3048056964 cites W2237158255 @default.
• W3048056964 cites W2604946918 @default.
• W3048056964 cites W2791950347 @default.
• W3048056964 cites W2962735187 @default.
• W3048056964 cites W2962901934 @default.
• W3048056964 cites W2962902250 @default.
• W3048056964 cites W2962949156 @default.
• W3048056964 cites W2963582321 @default.
• W3048056964 cites W2963750583 @default.
• W3048056964 cites W2964278219 @default.
• W3048056964 cites W2964299116 @default.
• W3048056964 cites W2985924367 @default.
• W3048056964 cites W3007421276 @default.
• W3048056964 doi "https://doi.org/10.1609/aaai.v35i10.17082" @default.
• W3048056964 hasPublicationYear "2021" @default.
• W3048056964 type Work @default.
• W3048056964 sameAs 3048056964 @default.
• W3048056964 citedByCount "1" @default.
• W3048056964 countsByYear W30480569642021 @default.
• W3048056964 crossrefType "journal-article" @default.
• W3048056964 hasAuthorship W3048056964A5018784842 @default.
• W3048056964 hasAuthorship W3048056964A5036260775 @default.
• W3048056964 hasBestOaLocation W30480569641 @default.
• W3048056964 hasConcept C119857082 @default.
• W3048056964 hasConcept C121332964 @default.
• W3048056964 hasConcept C126255220 @default.
• W3048056964 hasConcept C134306372 @default.
• W3048056964 hasConcept C144237770 @default.
• W3048056964 hasConcept C199360897 @default.
• W3048056964 hasConcept C2777027219 @default.
• W3048056964 hasConcept C2780791683 @default.
• W3048056964 hasConcept C33923547 @default.
• W3048056964 hasConcept C34388435 @default.
• W3048056964 hasConcept C41008148 @default.
• W3048056964 hasConcept C50817715 @default.
• W3048056964 hasConcept C62520636 @default.
• W3048056964 hasConcept C73602740 @default.
• W3048056964 hasConcept C77553402 @default.
• W3048056964 hasConceptScore W3048056964C119857082 @default.
• W3048056964 hasConceptScore W3048056964C121332964 @default.
• W3048056964 hasConceptScore W3048056964C126255220 @default.
• W3048056964 hasConceptScore W3048056964C134306372 @default.
• W3048056964 hasConceptScore W3048056964C144237770 @default.
• W3048056964 hasConceptScore W3048056964C199360897 @default.
• W3048056964 hasConceptScore W3048056964C2777027219 @default.
• W3048056964 hasConceptScore W3048056964C2780791683 @default.
• W3048056964 hasConceptScore W3048056964C33923547 @default.
• W3048056964 hasConceptScore W3048056964C34388435 @default.
• W3048056964 hasConceptScore W3048056964C41008148 @default.
• W3048056964 hasConceptScore W3048056964C50817715 @default.
• W3048056964 hasConceptScore W3048056964C62520636 @default.
• W3048056964 hasConceptScore W3048056964C73602740 @default.
• W3048056964 hasConceptScore W3048056964C77553402 @default.
• W3048056964 hasIssue "10" @default.
• W3048056964 hasLocation W30480569641 @default.
• W3048056964 hasLocation W30480569642 @default.
• W3048056964 hasOpenAccess W3048056964 @default.
• W3048056964 hasPrimaryLocation W30480569641 @default.
• W3048056964 hasRelatedWork W1600255059 @default.
• W3048056964 hasRelatedWork W2139129601 @default.
• W3048056964 hasRelatedWork W2141645258 @default.
• W3048056964 hasRelatedWork W2752599163 @default.
• W3048056964 hasRelatedWork W2951802169 @default.
• W3048056964 hasRelatedWork W2963382851 @default.
• W3048056964 hasRelatedWork W2964125852 @default.
• W3048056964 hasRelatedWork W3002095816 @default.
• W3048056964 hasRelatedWork W4318620749 @default.
• W3048056964 hasRelatedWork W4367190832 @default.
• W3048056964 hasVolume "35" @default.
• W3048056964 isParatext "false" @default.
• W3048056964 isRetracted "false" @default.
• W3048056964 magId "3048056964" @default.

• next