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 1181–1190 of 1262 papers

TitleStatusHype
Decentralized Cooperative Stochastic BanditsCode0
Gaussian Gated Linear NetworksCode0
Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous ActionsCode0
(Almost) Free Incentivized Exploration from Decentralized Learning AgentsCode0
Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace RecoveryCode0
MABSplit: Faster Forest Training Using Multi-Armed BanditsCode0
Risk-Aware Continuous Control with Neural Contextual BanditsCode0
Thompson Sampling for Linearly Constrained BanditsCode0
Bayesian Optimisation over Multiple Continuous and Categorical InputsCode0
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCode0
Show:102550
← PrevPage 119 of 127Next →

Benchmark Results

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