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 1221–1230 of 1262 papers

TitleStatusHype
Communication Efficient Distributed Learning for Kernelized Contextual Bandits—0
Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity—0
Competing Bandits in Matching Markets—0
Competing Bandits: The Perils of Exploration Under Competition—0
Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs—0
Concurrent Decentralized Channel Allocation and Access Point Selection using Multi-Armed Bandits in multi BSS WLANs—0
Confidence-Budget Matching for Sequential Budgeted Learning—0
Conformal Off-Policy Prediction in Contextual Bandits—0
Conservative Contextual Bandits: Beyond Linear Representations—0
Constant regret for sequence prediction with limited advice—0
Show:102550
← PrevPage 123 of 127Next →

Benchmark Results

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