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 151–160 of 1262 papers

TitleStatusHype
Linear Contextual Bandits with Interference—0
Second Order Bounds for Contextual Bandits with Function Approximation—0
Designing an Interpretable Interface for Contextual Bandits—0
Causal Feature Selection Method for Contextual Multi-Armed Bandits in Recommender System—0
Partially Observable Contextual Bandits with Linear Payoffs—0
Batched Online Contextual Sparse Bandits with Sequential Inclusion of Features—0
Batch Ensemble for Variance Dependent Regret in Stochastic Bandits—0
A Hybrid Meta-Learning and Multi-Armed Bandit Approach for Context-Specific Multi-Objective Recommendation Optimization—0
Modified Meta-Thompson Sampling for Linear Bandits and Its Bayes Regret Analysis—0
Faster Q-Learning Algorithms for Restless Bandits—0
Show:102550
← PrevPage 16 of 127Next →

Benchmark Results

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