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 561–570 of 1262 papers

TitleStatusHype
Continuous K-Max Bandits—0
Bandit Social Learning: Exploration under Myopic Behavior—0
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems—0
Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making—0
Bandits meet Computer Architecture: Designing a Smartly-allocated Cache—0
Algorithms for Differentially Private Multi-Armed Bandits—0
Contextual Pandora's Box—0
Contextual Online Decision Making with Infinite-Dimensional Functional Regression—0
Bandits for Learning to Explain from Explanations—0
Contextual Multinomial Logit Bandits with General Value Functions—0
Show:102550
← PrevPage 57 of 127Next →

Benchmark Results

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