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 881–890 of 1262 papers

TitleStatusHype
Selective Reviews of Bandit Problems in AI via a Statistical View—0
Selfish Robustness and Equilibria in Multi-Player Bandits—0
Self-Supervised Contextual Bandits in Computer Vision—0
Self-Tuning Bandits over Unknown Covariate-Shifts—0
Semantic Parsing for Planning Goals as Constrained Combinatorial Contextual Bandits—0
Semi-Parametric Batched Global Multi-Armed Bandits with Covariates—0
Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization—0
Sequential Batch Learning in Finite-Action Linear Contextual Bandits—0
Sequential Best-Arm Identification with Application to Brain-Computer Interface—0
Constrained Restless Bandits for Dynamic Scheduling in Cyber-Physical Systems—0
Show:102550
← PrevPage 89 of 127Next →

Benchmark Results

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