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 1091–1100 of 1262 papers

TitleStatusHype
An Empirical Evaluation of Federated Contextual Bandit Algorithms—0
An Empirical Evaluation of Thompson Sampling—0
A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free—0
A New Benchmark for Online Learning with Budget-Balancing Constraints—0
An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System—0
An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits—0
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit—0
An Instrumental Value for Data Production and its Application to Data Pricing—0
An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays—0
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits—0
Show:102550
← PrevPage 110 of 127Next →

Benchmark Results

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