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 61–70 of 1262 papers

TitleStatusHype
Adversarial Bandits with Knapsacks—0
Adversarial Contextual Bandits Go Kernelized—0
Active Search for High Recall: a Non-Stationary Extension of Thompson Sampling—0
Adaptively Learning to Select-Rank in Online Platforms—0
A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits—0
Almost Boltzmann Exploration—0
An Analysis of Reinforcement Learning for Malaria Control—0
Active Reinforcement Learning: Observing Rewards at a Cost—0
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds—0
A KL-LUCB algorithm for Large-Scale Crowdsourcing—0
Show:102550
← PrevPage 7 of 127Next →

Benchmark Results

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