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 171–180 of 1262 papers

TitleStatusHype
Diminishing Exploration: A Minimalist Approach to Piecewise Stationary Multi-Armed Bandits—0
Stochastic Bandits for Egalitarian Assignment—0
Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks—0
EVOLvE: Evaluating and Optimizing LLMs For Exploration—0
DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback—0
High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions—0
Online Posterior Sampling with a Diffusion Prior—0
Minimax-optimal trust-aware multi-armed bandits—0
uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs—0
On Lai's Upper Confidence Bound in Multi-Armed Bandits—0
Show:102550
← PrevPage 18 of 127Next →

Benchmark Results

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