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 671–680 of 1262 papers

TitleStatusHype
Off-Policy Risk Assessment in Markov Decision Processes—0
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits—0
On conditional versus marginal bias in multi-armed bandits—0
On Differentially Private Federated Linear Contextual Bandits—0
On Finding the Largest Mean Among Many—0
On Interpolating Experts and Multi-Armed Bandits—0
On Kernelized Multi-armed Bandits—0
On Kernelized Multi-Armed Bandits with Constraints—0
On Lai's Upper Confidence Bound in Multi-Armed Bandits—0
On Learning to Rank Long Sequences with Contextual Bandits—0
Show:102550
← PrevPage 68 of 127Next →

Benchmark Results

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