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 461–470 of 1262 papers

TitleStatusHype
Exponentiated Gradient LINUCB for Contextual Multi-Armed Bandits—0
Exposure-Aware Recommendation using Contextual Bandits—0
Fair Algorithms for Infinite and Contextual Bandits—0
Fair Algorithms for Multi-Agent Multi-Armed Bandits—0
Bandit Learning with Delayed Impact of Actions—0
Fair Contextual Multi-Armed Bandits: Theory and Experiments—0
Fair Exploration via Axiomatic Bargaining—0
Fairness and Privacy Guarantees in Federated Contextual Bandits—0
Fairness and Welfare Quantification for Regret in Multi-Armed Bandits—0
Constant regret for sequence prediction with limited advice—0
Show:102550
← PrevPage 47 of 127Next →

Benchmark Results

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