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 621–630 of 1262 papers

TitleStatusHype
Privacy Amplification via Shuffling for Linear Contextual Bandits—0
Efficient Action Poisoning Attacks on Linear Contextual Bandits—0
Best Arm Identification under Additive Transfer Bandits—0
Contextual Bandit Applications in Customer Support Bot—0
On Submodular Contextual Bandits—0
Optimal Algorithms for Stochastic Contextual Preference Bandits—0
Identification of the Generalized Condorcet Winner in Multi-dueling BanditsCode0
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits—0
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and LearningCode0
Bandits with Knapsacks beyond the Worst Case—0
Show:102550
← PrevPage 63 of 127Next →

Benchmark Results

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