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 291–300 of 1262 papers

TitleStatusHype
Efficient Contextual Bandits with Uninformed Feedback Graphs—0
Stochastic contextual bandits with graph feedback: from independence number to MAS number—0
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning—0
Fast UCB-type algorithms for stochastic bandits with heavy and super heavy symmetric noise—0
Tree Ensembles for Contextual Bandits—0
Fairness of Exposure in Online Restless Multi-armed BanditsCode0
Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic BanditsCode0
Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits—0
Fairness and Privacy Guarantees in Federated Contextual Bandits—0
Off-Policy Evaluation of Slate Bandit Policies via Optimizing AbstractionCode0
Show:102550
← PrevPage 30 of 127Next →

Benchmark Results

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