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 161–170 of 1262 papers

TitleStatusHype
Federated Neural BanditsCode0
Finding All ε-Good Arms in Stochastic BanditsCode0
(Almost) Free Incentivized Exploration from Decentralized Learning AgentsCode0
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance AdaptationCode0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
Batched Multi-armed Bandits ProblemCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Active Feature Selection for the Mutual Information CriterionCode0
Bayesian Design Principles for Frequentist Sequential LearningCode0
Model selection for contextual banditsCode0
Show:102550
← PrevPage 17 of 127Next →

Benchmark Results

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