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 1081–1090 of 1262 papers

TitleStatusHype
Almost Boltzmann Exploration—0
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits—0
A Model Selection Approach for Corruption Robust Reinforcement Learning—0
An Adaptive Method for Contextual Stochastic Multi-armed Bandits with Rewards Generated by a Linear Dynamical System—0
Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits—0
An Analysis of Reinforcement Learning for Malaria Control—0
An Analysis of the Value of Information when Exploring Stochastic, Discrete Multi-Armed Bandits—0
A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits—0
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives—0
An Efficient Algorithm for Deep Stochastic Contextual Bandits—0
Show:102550
← PrevPage 109 of 127Next →

Benchmark Results

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