FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962748815> ?p ?o ?g. }

• W2962748815 endingPage "767" @default.
• W2962748815 startingPage "759" @default.
• W2962748815 abstract "In the Multi-Armed Bandit (MAB) problem, there is a given set of arms with unknown reward models. At each time, a player selects one arm to play, aiming to maximize the total expected reward over a horizon of length T. An approach based on a Deterministic Sequencing of Exploration and Exploitation (DSEE) is developed for constructing sequential arm selection policies. It is shown that for all light-tailed reward distributions, DSEE achieves the optimal logarithmic order of the regret, where regret is defined as the total expected reward loss against the ideal case with known reward models. For heavy-tailed reward distributions, DSEE achieves O(T <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1/p</sup> ) regret when the moments of the reward distributions exist up to the pth order for and O(T <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1/(1+p/2)</sup> ) for p > 2. With the knowledge of an upper bound on a finite moment of the heavy-tailed reward distributions, DSEE offers the optimal logarithmic regret order. The proposed DSEE approach complements existing work on MAB by providing corresponding results for general reward distributions. Furthermore, with a clearly defined tunable parameter-the cardinality of the exploration sequence, the DSEE approach is easily extendable to variations of MAB, including MAB with various objectives, decentralized MAB with multiple players and incomplete reward observations under collisions, restless MAB with unknown dynamics, and combinatorial MAB with dependent arms that often arise in network optimization problems such as the shortest path, the minimum spanning tree, and the dominating set problems under unknown random weights." @default.
• W2962748815 created "2019-07-30" @default.
• W2962748815 creator A5007144865 @default.
• W2962748815 creator A5009337709 @default.
• W2962748815 creator A5013788255 @default.
• W2962748815 date "2013-10-01" @default.
• W2962748815 modified "2023-10-03" @default.
• W2962748815 title "Deterministic Sequencing of Exploration and Exploitation for Multi-Armed Bandit Problems" @default.
• W2962748815 cites W1980829002 @default.
• W2962748815 cites W1998498767 @default.
• W2962748815 cites W2000080679 @default.
• W2962748815 cites W2009551863 @default.
• W2962748815 cites W2010189695 @default.
• W2962748815 cites W2012731843 @default.
• W2962748815 cites W2019923980 @default.
• W2962748815 cites W2041205077 @default.
• W2962748815 cites W2049689520 @default.
• W2962748815 cites W2093562354 @default.
• W2962748815 cites W2132418266 @default.
• W2962748815 cites W2140571193 @default.
• W2962748815 cites W2150328967 @default.
• W2962748815 cites W2168405694 @default.
• W2962748815 cites W2555652361 @default.
• W2962748815 cites W2962764550 @default.
• W2962748815 cites W3100779200 @default.
• W2962748815 cites W3102381603 @default.
• W2962748815 cites W3103604572 @default.
• W2962748815 cites W4233413206 @default.
• W2962748815 doi "https://doi.org/10.1109/jstsp.2013.2263494" @default.
• W2962748815 hasPublicationYear "2013" @default.
• W2962748815 type Work @default.
• W2962748815 sameAs 2962748815 @default.
• W2962748815 citedByCount "82" @default.
• W2962748815 countsByYear W29627488152013 @default.
• W2962748815 countsByYear W29627488152014 @default.
• W2962748815 countsByYear W29627488152015 @default.
• W2962748815 countsByYear W29627488152016 @default.
• W2962748815 countsByYear W29627488152017 @default.
• W2962748815 countsByYear W29627488152018 @default.
• W2962748815 countsByYear W29627488152019 @default.
• W2962748815 countsByYear W29627488152020 @default.
• W2962748815 countsByYear W29627488152021 @default.
• W2962748815 countsByYear W29627488152022 @default.
• W2962748815 countsByYear W29627488152023 @default.
• W2962748815 crossrefType "journal-article" @default.
• W2962748815 hasAuthorship W2962748815A5007144865 @default.
• W2962748815 hasAuthorship W2962748815A5009337709 @default.
• W2962748815 hasAuthorship W2962748815A5013788255 @default.
• W2962748815 hasBestOaLocation W29627488152 @default.
• W2962748815 hasConcept C10138342 @default.
• W2962748815 hasConcept C114614502 @default.
• W2962748815 hasConcept C119857082 @default.
• W2962748815 hasConcept C121332964 @default.
• W2962748815 hasConcept C123197309 @default.
• W2962748815 hasConcept C124101348 @default.
• W2962748815 hasConcept C126255220 @default.
• W2962748815 hasConcept C134306372 @default.
• W2962748815 hasConcept C162324750 @default.
• W2962748815 hasConcept C177264268 @default.
• W2962748815 hasConcept C179254644 @default.
• W2962748815 hasConcept C182306322 @default.
• W2962748815 hasConcept C199360897 @default.
• W2962748815 hasConcept C2778112365 @default.
• W2962748815 hasConcept C33923547 @default.
• W2962748815 hasConcept C39927690 @default.
• W2962748815 hasConcept C41008148 @default.
• W2962748815 hasConcept C50817715 @default.
• W2962748815 hasConcept C54355233 @default.
• W2962748815 hasConcept C74650414 @default.
• W2962748815 hasConcept C77553402 @default.
• W2962748815 hasConcept C86803240 @default.
• W2962748815 hasConcept C87117476 @default.
• W2962748815 hasConceptScore W2962748815C10138342 @default.
• W2962748815 hasConceptScore W2962748815C114614502 @default.
• W2962748815 hasConceptScore W2962748815C119857082 @default.
• W2962748815 hasConceptScore W2962748815C121332964 @default.
• W2962748815 hasConceptScore W2962748815C123197309 @default.
• W2962748815 hasConceptScore W2962748815C124101348 @default.
• W2962748815 hasConceptScore W2962748815C126255220 @default.
• W2962748815 hasConceptScore W2962748815C134306372 @default.
• W2962748815 hasConceptScore W2962748815C162324750 @default.
• W2962748815 hasConceptScore W2962748815C177264268 @default.
• W2962748815 hasConceptScore W2962748815C179254644 @default.
• W2962748815 hasConceptScore W2962748815C182306322 @default.
• W2962748815 hasConceptScore W2962748815C199360897 @default.
• W2962748815 hasConceptScore W2962748815C2778112365 @default.
• W2962748815 hasConceptScore W2962748815C33923547 @default.
• W2962748815 hasConceptScore W2962748815C39927690 @default.
• W2962748815 hasConceptScore W2962748815C41008148 @default.
• W2962748815 hasConceptScore W2962748815C50817715 @default.
• W2962748815 hasConceptScore W2962748815C54355233 @default.
• W2962748815 hasConceptScore W2962748815C74650414 @default.
• W2962748815 hasConceptScore W2962748815C77553402 @default.
• W2962748815 hasConceptScore W2962748815C86803240 @default.
• W2962748815 hasConceptScore W2962748815C87117476 @default.
• W2962748815 hasIssue "5" @default.
• W2962748815 hasLocation W29627488151 @default.
• W2962748815 hasLocation W29627488152 @default.

• next