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 1–10 of 1262 papers

TitleStatusHype
Hypothesis Generation with Large Language ModelsCode2
Off-Policy Evaluation for Large Action Spaces via EmbeddingsCode2
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior ModelCode2
Performance-bounded Online Ensemble Learning Method Based on Multi-armed bandits and Its Applications in Real-time Safety AssessmentCode1
Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming ProblemCode1
A unifying framework for generalised Bayesian online learning in non-stationary environmentsCode1
LASeR: Learning to Adaptively Select Reward Models with Multi-Armed BanditsCode1
Discovering Minimal Reinforcement Learning EnvironmentsCode1
In-Context Reinforcement Learning for Variable Action SpacesCode1
Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital HealthCode1
Show:102550
← PrevPage 1 of 127Next →

Benchmark Results

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