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 411–420 of 1262 papers

TitleStatusHype
Reward Teaching for Federated Multi-armed Bandits—0
Stochastic Contextual Bandits with Graph-based Contexts—0
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits—0
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded RewardsCode0
Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement LearningCode0
Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards—0
Optimal Activation of Halting Multi-Armed Bandit Models—0
A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed BanditsCode0
Learning Personalized Decision Support Policies—0
SmartChoices: Augmenting Software with Learned Implementations—0
Show:102550
← PrevPage 42 of 127Next →

Benchmark Results

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