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 641–650 of 1262 papers

TitleStatusHype
Contextual Bandit Applications in Customer Support Bot—0
On Submodular Contextual Bandits—0
Bandits with Knapsacks beyond the Worst Case—0
Identification of the Generalized Condorcet Winner in Multi-dueling BanditsCode0
Optimal Algorithms for Stochastic Contextual Preference Bandits—0
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and LearningCode0
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization—0
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits—0
Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits—0
Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits—0
Show:102550
← PrevPage 65 of 127Next →

Benchmark Results

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