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 41–50 of 1262 papers

TitleStatusHype
Sparse Additive Contextual Bandits: A Nonparametric Approach for Online Decision-making with High-dimensional Covariates—0
NeuroSep-CP-LCB: A Deep Learning-based Contextual Multi-armed Bandit Algorithm with Uncertainty Quantification for Early Sepsis PredictionCode0
Sparse Nonparametric Contextual Bandits—0
Performance-bounded Online Ensemble Learning Method Based on Multi-armed bandits and Its Applications in Real-time Safety AssessmentCode1
A New Benchmark for Online Learning with Budget-Balancing Constraints—0
Variance-Dependent Regret Lower Bounds for Contextual Bandits—0
Bi-Criteria Optimization for Combinatorial Bandits: Sublinear Regret and Constraint Violation under Bandit Feedback—0
Locally Private Nonparametric Contextual Multi-armed BanditsCode0
Multiplayer Information Asymmetric Contextual Bandits—0
Cost-Aware Optimal Pairwise Pure Exploration—0
Show:102550
← PrevPage 5 of 127Next →

Benchmark Results

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