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 81–90 of 1262 papers

TitleStatusHype
(Almost) Free Incentivized Exploration from Decentralized Learning AgentsCode0
Confidence Intervals for Policy Evaluation in Adaptive ExperimentsCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Adaptive Experimentation with Delayed Binary FeedbackCode0
Contextual bandits with entropy-based human feedbackCode0
A Convex Framework for Confounding Robust InferenceCode0
Corralling a Band of Bandit AlgorithmsCode0
Scalable Exploration via Ensemble++Code0
Causal Contextual Bandits with Adaptive ContextCode0
Show:102550
← PrevPage 9 of 127Next →

Benchmark Results

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