SOTAVerified

Multi-Armed Bandits

Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.

( Image credit: Microsoft Research )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1051–1060 of 1262 papers

TitleStatusHype
Adaptive Endpointing with Deep Contextual Multi-armed Bandits—0
Adaptive Exploration in Linear Contextual Bandit—0
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds—0
Adaptively Learning to Select-Rank in Online Platforms—0
Adaptive Regret for Bandits Made Possible: Two Queries Suffice—0
Adaptive, Robust and Scalable Bayesian Filtering for Online Learning—0
ADARES: Adaptive Resource Management for Virtual Machines—0
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health—0
Bandits with Knapsacks beyond the Worst-Case—0
Adversarial Attacks on Adversarial Bandits—0
Show:102550
← PrevPage 106 of 127Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified