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
Foundations of Reinforcement Learning and Interactive Decision Making—0
Best-of-Both-Worlds Linear Contextual Bandits—0
Harnessing the Power of Federated Learning in Federated Contextual BanditsCode0
Diversity-Based Recruitment in Crowdsensing By Combinatorial Multi-Armed Bandits—0
Zero-Inflated Bandits—0
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits—0
Neural Contextual Bandits for Personalized Recommendation—0
In-Context Reinforcement Learning for Variable Action SpacesCode1
Bayesian Analysis of Combinatorial Gaussian Process Bandits—0
Distribution-Dependent Rates for Multi-Distribution Learning—0
Show:102550
← PrevPage 29 of 127Next →

Benchmark Results

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