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 1081–1090 of 1262 papers

TitleStatusHype
Correlated Multi-armed Bandits with a Latent Random SourceCode0
Data Poisoning Attacks in Contextual Bandits—0
Nonparametric Gaussian Mixture Models for the Multi-Armed BanditCode0
On-line Adaptative Curriculum Learning for GANsCode0
Preference-based Online Learning with Dueling Bandits: A Survey—0
Deep Contextual Multi-armed Bandits—0
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits—0
Linear Bandits with Stochastic Delayed Feedback—0
Multi-User Multi-Armed Bandits for Uncoordinated Spectrum Access—0
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems—0
Show:102550
← PrevPage 109 of 127Next →

Benchmark Results

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