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 901–910 of 1262 papers

TitleStatusHype
Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs—0
Small-loss bounds for online learning with partial information—0
Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness—0
SmartChoices: Augmenting Software with Learned Implementations—0
Smoothed Online Learning is as Easy as Statistical Learning—0
Smooth Sequential Optimisation with Delayed Feedback—0
Social Learning in Multi Agent Multi Armed Bandits—0
Sparse Additive Contextual Bandits: A Nonparametric Approach for Online Decision-making with High-dimensional Covariates—0
Sparse Nonparametric Contextual Bandits—0
Sparsity, variance and curvature in multi-armed bandits—0
Show:102550
← PrevPage 91 of 127Next →

Benchmark Results

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