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 501–510 of 1262 papers

TitleStatusHype
Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation—0
Competing Bandits in Matching Markets—0
Finite-Time Analysis of Kernelised Contextual Bandits—0
Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation—0
Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments—0
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits—0
Fixed-Budget Best-Arm Identification in Structured Bandits—0
FLASH: Federated Learning Across Simultaneous Heterogeneities—0
Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles—0
α-Fair Contextual Bandits—0
Show:102550
← PrevPage 51 of 127Next →

Benchmark Results

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