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 1171–1180 of 1262 papers

TitleStatusHype
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many ArmsCode0
Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual BanditsCode0
A Convex Framework for Confounding Robust InferenceCode0
From Restless to Contextual: A Thresholding Bandit Approach to Improve Finite-horizon PerformanceCode0
From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance AdaptationCode0
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling BanditsCode0
Networked Restless Bandits with Positive ExternalitiesCode0
Locally Differentially Private (Contextual) Bandits LearningCode0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Locally Private Nonparametric Contextual Multi-armed BanditsCode0
Show:102550
← PrevPage 118 of 127Next →

Benchmark Results

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