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 601–610 of 1262 papers

TitleStatusHype
Approximate Function Evaluation via Multi-Armed Bandits—0
Reinforced Meta Active Learning—0
Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits—0
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits—0
Restless Multi-Armed Bandits under Exogenous Global Markov Process—0
Federated Online Sparse Decision Making—0
Truncated LinUCB for Stochastic Linear BanditsCode0
The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication—0
Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits—0
Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences—0
Show:102550
← PrevPage 61 of 127Next →

Benchmark Results

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