Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203539123> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3203539123 endingPage "2922" @default.
- W3203539123 startingPage "2908" @default.
- W3203539123 abstract "We study a family of adversarial (a.k.a. nonstochastic) multi-armed bandit (MAB) problems, wherein not only the player cannot observe the reward on the played arm (self-unaware player) but also it incurs switching costs when shifting to another arm. We study two cases: In Case 1, at each round, the player is able to either play or observe the chosen arm, but not both. In Case 2, the player can choose an arm to play and, at the same round, choose another arm to observe. In both cases, the player incurs a cost for consecutive arm switching due to playing or observing the arms. We propose two novel online learning-based algorithms each addressing one of the aforementioned MAB problems. We theoretically prove that the proposed algorithms for Case 1 and Case 2 achieve sublinear regret of O(√[4]KT3lnK) and O(√[3](K-1)T2lnK) , respectively, where the latter regret bound is order-optimal in time, K is the number of arms, and T is the total number of rounds. In Case 2, we extend the player's capability to multiple observations and show that more observations do not necessarily improve the regret bound due to incurring switching costs. However, we derive an upper bound for switching cost as c ≤ 1/√[3]m2 for which the regret bound is improved as the number of observations increases. Finally, through this study, we found that a generalized version of our approach gives an interesting sublinear regret upper bound result of [Formula: see text] for any self-unaware bandit player with s number of binary decision dilemma before taking the action. To further validate and complement the theoretical findings, we conduct extensive performance evaluations over synthetic data constructed by nonstochastic MAB environment simulations and wireless spectrum measurement data collected in a real-world experiment." @default.
- W3203539123 created "2021-10-11" @default.
- W3203539123 creator A5049398754 @default.
- W3203539123 creator A5064265263 @default.
- W3203539123 creator A5078480632 @default.
- W3203539123 date "2023-06-01" @default.
- W3203539123 modified "2023-10-12" @default.
- W3203539123 title "Self-Unaware Adversarial Multi-Armed Bandits With Switching Costs" @default.
- W3203539123 cites W1975903663 @default.
- W3203539123 cites W1988790447 @default.
- W3203539123 cites W2009551863 @default.
- W3203539123 cites W2039282619 @default.
- W3203539123 cites W2077902449 @default.
- W3203539123 cites W2093825590 @default.
- W3203539123 cites W2109690147 @default.
- W3203539123 cites W2142971854 @default.
- W3203539123 cites W2158319693 @default.
- W3203539123 cites W2159928341 @default.
- W3203539123 cites W2168405694 @default.
- W3203539123 cites W2591459227 @default.
- W3203539123 cites W2743003320 @default.
- W3203539123 cites W2795957874 @default.
- W3203539123 cites W2884396969 @default.
- W3203539123 cites W2906849663 @default.
- W3203539123 cites W2950929549 @default.
- W3203539123 cites W2963784584 @default.
- W3203539123 cites W2988311143 @default.
- W3203539123 cites W3125634603 @default.
- W3203539123 cites W4206275166 @default.
- W3203539123 cites W4233287798 @default.
- W3203539123 doi "https://doi.org/10.1109/tnnls.2021.3110194" @default.
- W3203539123 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34587093" @default.
- W3203539123 hasPublicationYear "2023" @default.
- W3203539123 type Work @default.
- W3203539123 sameAs 3203539123 @default.
- W3203539123 citedByCount "0" @default.
- W3203539123 crossrefType "journal-article" @default.
- W3203539123 hasAuthorship W3203539123A5049398754 @default.
- W3203539123 hasAuthorship W3203539123A5064265263 @default.
- W3203539123 hasAuthorship W3203539123A5078480632 @default.
- W3203539123 hasConcept C10138342 @default.
- W3203539123 hasConcept C114614502 @default.
- W3203539123 hasConcept C117160843 @default.
- W3203539123 hasConcept C119857082 @default.
- W3203539123 hasConcept C126255220 @default.
- W3203539123 hasConcept C134306372 @default.
- W3203539123 hasConcept C154945302 @default.
- W3203539123 hasConcept C162324750 @default.
- W3203539123 hasConcept C182306322 @default.
- W3203539123 hasConcept C33923547 @default.
- W3203539123 hasConcept C37736160 @default.
- W3203539123 hasConcept C41008148 @default.
- W3203539123 hasConcept C50817715 @default.
- W3203539123 hasConcept C77553402 @default.
- W3203539123 hasConceptScore W3203539123C10138342 @default.
- W3203539123 hasConceptScore W3203539123C114614502 @default.
- W3203539123 hasConceptScore W3203539123C117160843 @default.
- W3203539123 hasConceptScore W3203539123C119857082 @default.
- W3203539123 hasConceptScore W3203539123C126255220 @default.
- W3203539123 hasConceptScore W3203539123C134306372 @default.
- W3203539123 hasConceptScore W3203539123C154945302 @default.
- W3203539123 hasConceptScore W3203539123C162324750 @default.
- W3203539123 hasConceptScore W3203539123C182306322 @default.
- W3203539123 hasConceptScore W3203539123C33923547 @default.
- W3203539123 hasConceptScore W3203539123C37736160 @default.
- W3203539123 hasConceptScore W3203539123C41008148 @default.
- W3203539123 hasConceptScore W3203539123C50817715 @default.
- W3203539123 hasConceptScore W3203539123C77553402 @default.
- W3203539123 hasFunder F4320308943 @default.
- W3203539123 hasFunder F4320309355 @default.
- W3203539123 hasFunder F4320338281 @default.
- W3203539123 hasIssue "6" @default.
- W3203539123 hasLocation W32035391231 @default.
- W3203539123 hasLocation W32035391232 @default.
- W3203539123 hasOpenAccess W3203539123 @default.
- W3203539123 hasPrimaryLocation W32035391231 @default.
- W3203539123 hasRelatedWork W1947085858 @default.
- W3203539123 hasRelatedWork W2101991911 @default.
- W3203539123 hasRelatedWork W2155070487 @default.
- W3203539123 hasRelatedWork W2174986909 @default.
- W3203539123 hasRelatedWork W2527791220 @default.
- W3203539123 hasRelatedWork W2949801578 @default.
- W3203539123 hasRelatedWork W3039767703 @default.
- W3203539123 hasRelatedWork W3123835761 @default.
- W3203539123 hasRelatedWork W4311589891 @default.
- W3203539123 hasRelatedWork W4376155396 @default.
- W3203539123 hasVolume "34" @default.
- W3203539123 isParatext "false" @default.
- W3203539123 isRetracted "false" @default.
- W3203539123 magId "3203539123" @default.
- W3203539123 workType "article" @default.