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 1111–1120 of 1262 papers

TitleStatusHype
On-line Adaptative Curriculum Learning for GANsCode0
Bandit-Based Monte Carlo Optimization for Nearest NeighborsCode0
Quantile Bandits for Best Arms IdentificationCode0
Adaptive Linear Estimating EquationsCode0
Latent Bottlenecked Attentive Neural ProcessesCode0
Multi-armed Bandits with Missing OutcomeCode0
Multi-Armed Bandits with Network InterferenceCode0
Residual Loss Prediction: Reinforcement Learning With No Incremental FeedbackCode0
Multi-facet Contextual Bandits: A Neural Network PerspectiveCode0
Smoothness-Adaptive Contextual BanditsCode0
Show:102550
← PrevPage 112 of 127Next →

Benchmark Results

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