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
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health—0
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits—0
Incentivized Exploration via Filtered Posterior Sampling—0
Efficient Prompt Optimization Through the Lens of Best Arm Identification—0
Diffusion Models Meet Contextual Bandits with Large Action Spaces—0
Thompson Sampling in Partially Observable Contextual Bandits—0
Thresholding Data Shapley for Data Cleansing Using Multi-Armed Bandits—0
FLASH: Federated Learning Across Simultaneous Heterogeneities—0
Contextual Multinomial Logit Bandits with General Value Functions—0
Efficient Contextual Bandits with Uninformed Feedback Graphs—0
Show:102550
← PrevPage 29 of 127Next →

Benchmark Results

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