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 491–500 of 1262 papers

TitleStatusHype
Batch Ensemble for Variance Dependent Regret in Stochastic Bandits—0
FedMABA: Towards Fair Federated Learning through Multi-Armed Bandits Allocation—0
Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning—0
Feel-Good Thompson Sampling for Contextual Dueling Bandits—0
Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits—0
Fighting Contextual Bandits with Stochastic Smoothing—0
Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy—0
Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health—0
Finding the bandit in a graph: Sequential search-and-stop—0
Batched Thompson Sampling for Multi-Armed Bandits—0
Show:102550
← PrevPage 50 of 127Next →

Benchmark Results

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