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 1051–1060 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
Show:102550
← PrevPage 106 of 127Next →

Benchmark Results

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