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 1021–1030 of 1262 papers

TitleStatusHype
Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits—0
Batched Multi-armed Bandits ProblemCode0
A Survey on Practical Applications of Multi-Armed and Contextual Bandits—0
Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits—0
Meta-Learning surrogate models for sequential decision making—0
Contextual Bandits with Random Projection—0
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox OptimizationCode0
Perturbed-History Exploration in Stochastic Multi-Armed Bandits—0
Better Algorithms for Stochastic Bandits with Adversarial Corruptions—0
AdaLinUCB: Opportunistic Learning for Contextual Bandits—0
Show:102550
← PrevPage 103 of 127Next →

Benchmark Results

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