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 891–900 of 1262 papers

TitleStatusHype
Sequential Design for Ranking Response Surfaces—0
Sequential Monte Carlo Bandits—0
Settling the Communication Complexity for Distributed Offline Reinforcement Learning—0
SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features—0
Sharp Analysis for KL-Regularized Contextual Bandits and RLHF—0
Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms—0
Shuffle Private Linear Contextual Bandits—0
Simple Regret Minimization for Contextual Bandits—0
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition—0
Skyline Identification in Multi-Armed Bandits—0
Show:102550
← PrevPage 90 of 127Next →

Benchmark Results

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