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 361–370 of 1262 papers

TitleStatusHype
Efficient Prompt Optimization Through the Lens of Best Arm Identification—0
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives—0
Differentially Private Multi-Armed Bandits in the Shuffle Model—0
Differentially Private Kernelized Contextual Bandits—0
Diffusion Models Meet Contextual Bandits with Large Action Spaces—0
Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits—0
Be Greedy in Multi-Armed Bandits—0
Discrete Choice Multi-Armed Bandits—0
Disentangling Exploration from Exploitation—0
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards—0
Show:102550
← PrevPage 37 of 127Next →

Benchmark Results

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