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 91–100 of 1262 papers

TitleStatusHype
Optimal Multi-Objective Best Arm Identification with Fixed Confidence—0
Efficient Implementation of LinearUCB through Algorithmic Improvements and Vector Computing Acceleration for Embedded Learning Systems—0
Heterogeneous Multi-Player Multi-Armed Bandits Robust To Adversarial Attacks—0
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness—0
Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy—0
Neural Risk-sensitive Satisficing in Contextual Bandits—0
Differentially Private Kernelized Contextual Bandits—0
On The Statistical Complexity of Offline Decision-Making—0
Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation—0
An Instrumental Value for Data Production and its Application to Data Pricing—0
Show:102550
← PrevPage 10 of 127Next →

Benchmark Results

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