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 901–925 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
SPRT-based Efficient Best Arm Identification in Stochastic Bandits—0
Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits—0
Stability Enforced Bandit Algorithms for Channel Selection in Remote State Estimation of Gauss-Markov Processes—0
Stabilizing the Kumaraswamy Distribution—0
Stateful Offline Contextual Policy Evaluation and Learning—0
Statistical Inference with M-Estimators on Adaptively Collected Data—0
Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits—0
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits—0
Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond—0
Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling—0
Stochastic Bandits for Egalitarian Assignment—0
Stochastic Bandits with Linear Constraints—0
Stochastic Bandits with Vector Losses: Minimizing ^-Norm of Relative Losses—0
Stochastic Contextual Bandits with Graph-based Contexts—0
Stochastic contextual bandits with graph feedback: from independence number to MAS number—0
Show:102550
← PrevPage 37 of 51Next →

Benchmark Results

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