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 231–240 of 1262 papers

TitleStatusHype
Approximating a Target Distribution using Weight QueriesCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Myopic Bayesian Design of Experiments via Posterior Sampling and Probabilistic ProgrammingCode0
Solving Inverse Problem for Multi-armed Bandits via Convex OptimizationCode0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Combinatorial Multi-armed Bandits for Resource AllocationCode0
Taming the Monster: A Fast and Simple Algorithm for Contextual BanditsCode0
Test-Time Scaling of Diffusion Models via Noise Trajectory SearchCode0
Adapting multi-armed bandits policies to contextual bandits scenariosCode0
Variational inference for the multi-armed contextual banditCode0
Show:102550
← PrevPage 24 of 127Next →

Benchmark Results

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