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 471–480 of 1262 papers

TitleStatusHype
Fairness in Learning: Classic and Contextual Bandits—0
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing—0
Fairness of Exposure in Stochastic Bandits—0
A Regret bound for Non-stationary Multi-Armed Bandits with Fairness Constraints—0
Falsification of Multiple Requirements for Cyber-Physical Systems Using Online Generative Adversarial Networks and Multi-Armed Bandits—0
Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits—0
Combinatorial Multi-Armed Bandits with Filtered Feedback—0
Faster Maximum Inner Product Search in High Dimensions—0
Constant regret for sequence prediction with limited advice—0
Asymptotic Convergence of Thompson Sampling—0
Show:102550
← PrevPage 48 of 127Next →

Benchmark Results

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