Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989755241> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2989755241 abstract "We consider the stochastic multi-armed bandit (MAB) problem in a setting where a player can pay to pre-observe arm rewards before playing an arm in each round. Apart from the usual trade-off between exploring new arms to find the best one and exploiting the arm believed to offer the highest reward, we encounter an additional dilemma: pre-observing more arms gives a higher chance to play the best one, but incurs a larger cost. For the single-player setting, we design an Observe-Before-Play Upper Confidence Bound (OBP-UCB) algorithm for $K$ arms with Bernoulli rewards, and prove a $T$-round regret upper bound $O(K^2log T)$. In the multi-player setting, collisions will occur when players select the same arm to play in the same round. We design a centralized algorithm, C-MP-OBP, and prove its $T$-round regret relative to an offline greedy strategy is upper bounded in $O(frac{K^4}{M^2}log T)$ for $K$ arms and $M$ players. We also propose distributed versions of the C-MP-OBP policy, called D-MP-OBP and D-MP-Adapt-OBP, achieving logarithmic regret with respect to collision-free target policies. Experiments on synthetic data and wireless channel traces show that C-MP-OBP and D-MP-OBP outperform random heuristics and offline optimal policies that do not allow pre-observations." @default.
- W2989755241 created "2019-12-05" @default.
- W2989755241 creator A5080529523 @default.
- W2989755241 creator A5085050673 @default.
- W2989755241 creator A5085243096 @default.
- W2989755241 date "2019-11-21" @default.
- W2989755241 modified "2023-09-23" @default.
- W2989755241 title "Observe Before Play: Multi-armed Bandit with Pre-observations" @default.
- W2989755241 cites W1882177676 @default.
- W2989755241 cites W1900560890 @default.
- W2989755241 cites W1975967782 @default.
- W2989755241 cites W2004335587 @default.
- W2989755241 cites W2009551863 @default.
- W2989755241 cites W2029199203 @default.
- W2989755241 cites W2049934117 @default.
- W2989755241 cites W2064895747 @default.
- W2989755241 cites W2140571193 @default.
- W2989755241 cites W2146025745 @default.
- W2989755241 cites W2168405694 @default.
- W2989755241 cites W2336073403 @default.
- W2989755241 cites W2443763917 @default.
- W2989755241 cites W2747326491 @default.
- W2989755241 cites W2796280559 @default.
- W2989755241 cites W2804242129 @default.
- W2989755241 cites W2804679153 @default.
- W2989755241 cites W2962847184 @default.
- W2989755241 cites W2962853044 @default.
- W2989755241 cites W2962934197 @default.
- W2989755241 cites W2964240248 @default.
- W2989755241 cites W2964245734 @default.
- W2989755241 cites W2320973428 @default.
- W2989755241 cites W2790561258 @default.
- W2989755241 doi "https://doi.org/10.48550/arxiv.1911.09458" @default.
- W2989755241 hasPublicationYear "2019" @default.
- W2989755241 type Work @default.
- W2989755241 sameAs 2989755241 @default.
- W2989755241 citedByCount "0" @default.
- W2989755241 crossrefType "posted-content" @default.
- W2989755241 hasAuthorship W2989755241A5080529523 @default.
- W2989755241 hasAuthorship W2989755241A5085050673 @default.
- W2989755241 hasAuthorship W2989755241A5085243096 @default.
- W2989755241 hasBestOaLocation W29897552411 @default.
- W2989755241 hasConcept C114614502 @default.
- W2989755241 hasConcept C118615104 @default.
- W2989755241 hasConcept C119857082 @default.
- W2989755241 hasConcept C121332964 @default.
- W2989755241 hasConcept C123197309 @default.
- W2989755241 hasConcept C126255220 @default.
- W2989755241 hasConcept C127705205 @default.
- W2989755241 hasConcept C134306372 @default.
- W2989755241 hasConcept C152361515 @default.
- W2989755241 hasConcept C33923547 @default.
- W2989755241 hasConcept C34388435 @default.
- W2989755241 hasConcept C39927690 @default.
- W2989755241 hasConcept C41008148 @default.
- W2989755241 hasConcept C50817715 @default.
- W2989755241 hasConcept C63553672 @default.
- W2989755241 hasConcept C77553402 @default.
- W2989755241 hasConcept C97355855 @default.
- W2989755241 hasConceptScore W2989755241C114614502 @default.
- W2989755241 hasConceptScore W2989755241C118615104 @default.
- W2989755241 hasConceptScore W2989755241C119857082 @default.
- W2989755241 hasConceptScore W2989755241C121332964 @default.
- W2989755241 hasConceptScore W2989755241C123197309 @default.
- W2989755241 hasConceptScore W2989755241C126255220 @default.
- W2989755241 hasConceptScore W2989755241C127705205 @default.
- W2989755241 hasConceptScore W2989755241C134306372 @default.
- W2989755241 hasConceptScore W2989755241C152361515 @default.
- W2989755241 hasConceptScore W2989755241C33923547 @default.
- W2989755241 hasConceptScore W2989755241C34388435 @default.
- W2989755241 hasConceptScore W2989755241C39927690 @default.
- W2989755241 hasConceptScore W2989755241C41008148 @default.
- W2989755241 hasConceptScore W2989755241C50817715 @default.
- W2989755241 hasConceptScore W2989755241C63553672 @default.
- W2989755241 hasConceptScore W2989755241C77553402 @default.
- W2989755241 hasConceptScore W2989755241C97355855 @default.
- W2989755241 hasLocation W29897552411 @default.
- W2989755241 hasLocation W29897552412 @default.
- W2989755241 hasOpenAccess W2989755241 @default.
- W2989755241 hasPrimaryLocation W29897552411 @default.
- W2989755241 hasRelatedWork W1487320471 @default.
- W2989755241 hasRelatedWork W2014128265 @default.
- W2989755241 hasRelatedWork W2158858912 @default.
- W2989755241 hasRelatedWork W2761816627 @default.
- W2989755241 hasRelatedWork W2893129234 @default.
- W2989755241 hasRelatedWork W2996735312 @default.
- W2989755241 hasRelatedWork W3034590885 @default.
- W2989755241 hasRelatedWork W3157633619 @default.
- W2989755241 hasRelatedWork W4302307106 @default.
- W2989755241 hasRelatedWork W4367190832 @default.
- W2989755241 isParatext "false" @default.
- W2989755241 isRetracted "false" @default.
- W2989755241 magId "2989755241" @default.
- W2989755241 workType "article" @default.