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 281–290 of 1262 papers

TitleStatusHype
Contextual bandits with concave rewards, and an application to fair ranking—0
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting—0
Contextual Bandits with Cross-learning—0
Balancing Act: Prioritization Strategies for LLM-Designed Restless Bandit Rewards—0
Asymptotic Randomised Control with applications to bandits—0
Contextual Bandits with Knapsacks for a Conversion Model—0
Contextual Bandits with Latent Confounders: An NMF Approach—0
Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks—0
Contextual Bandits with Online Neural Regression—0
A Federated Online Restless Bandit Framework for Cooperative Resource Allocation—0
Show:102550
← PrevPage 29 of 127Next →

Benchmark Results

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