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 1051–1075 of 1262 papers

TitleStatusHype
Balanced Linear Contextual Bandits—0
ADARES: Adaptive Resource Management for Virtual Machines—0
Contextual Combinatorial Multi-armed Bandits with Volatile Arms and Submodular Reward—0
Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task—0
A Bandit Approach to Sequential Experimental Design with False Discovery Control—0
Stochastic Top-K Subset Bandits with Linear Space and Non-Linear Feedback—0
Adversarial Bandits with Knapsacks—0
Kernel-based Multi-Task Contextual Bandits in Cellular Network Configuration—0
Rotting bandits are not harder than stochastic ones—0
Bandits with Temporal Stochastic Constraints—0
Decentralized Exploration in Multi-Armed Bandits -- Extended version—0
Best Arm Identification in Linked Bandits—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
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
Regularized Contextual Bandits—0
Fighting Contextual Bandits with Stochastic Smoothing—0
Decentralized Cooperative Stochastic BanditsCode0
Thompson Sampling Algorithms for Cascading Bandits—0
Contextual Multi-Armed Bandits for Causal Marketing—0
Show:102550
← PrevPage 43 of 51Next →

Benchmark Results

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