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 1061–1070 of 1262 papers

TitleStatusHype
Decentralized Exploration in Multi-Armed Bandits -- Extended version—0
Sample complexity of partition identification using multi-armed bandits—0
Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits—0
Adapting multi-armed bandits policies to contextual bandits scenariosCode0
Practical Bayesian Learning of Neural Networks via Adaptive Optimisation MethodsCode0
Multi-armed Bandits with Compensation—0
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions ModelingCode1
Stay With Me: Lifetime Maximization Through Heteroscedastic Linear Bandits With RenegingCode0
Online learning with feedback graphs and switching costs—0
Simple Regret Minimization for Contextual Bandits—0
Show:102550
← PrevPage 107 of 127Next →

Benchmark Results

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