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 221–230 of 1262 papers

TitleStatusHype
AdaLinUCB: Opportunistic Learning for Contextual Bandits—0
Confidence-Budget Matching for Sequential Budgeted Learning—0
Balanced Linear Contextual Bandits—0
Classical Bandit Algorithms for Entanglement Detection in Parameterized Qubit States—0
Clustered Linear Contextual Bandits with Knapsacks—0
COBRA: Contextual Bandit Algorithm for Ensuring Truthful Strategic Agents—0
Parallel Best Arm Identification in Heterogeneous Environments—0
Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Bandits—0
Collaborative Min-Max Regret in Grouped Multi-Armed Bandits—0
A framework for optimizing COVID-19 testing policy using a Multi Armed Bandit approach—0
Show:102550
← PrevPage 23 of 127Next →

Benchmark Results

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