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 321–330 of 1262 papers

TitleStatusHype
An Instrumental Value for Data Production and its Application to Data Pricing—0
Breaking the T Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits—0
Breaking the (1/Δ_2) Barrier: Better Batched Best Arm Identification with Adaptive Grids—0
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit—0
Adaptive Regret for Bandits Made Possible: Two Queries Suffice—0
Bounded Regret for Finitely Parameterized Multi-Armed Bandits—0
Boundary Crossing Probabilities for General Exponential Families—0
An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits—0
Bootstrapping Upper Confidence Bound—0
An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System—0
Show:102550
← PrevPage 33 of 127Next →

Benchmark Results

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