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 431–440 of 1262 papers

TitleStatusHype
Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning—0
Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback—0
Efficient Reinforcement Learning via Initial Pure Exploration—0
Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits—0
Efficient Training of Multi-task Combinarotial Neural Solver with Multi-armed Bandits—0
Empathic Responding for Digital Interpersonal Emotion Regulation via Content Recommendation—0
A General Reduction for High-Probability Analysis with General Light-Tailed Distributions—0
ε-Neural Thompson Sampling of Deep Brain Stimulation for Parkinson Disease Treatment—0
Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing—0
Equipping Experts/Bandits with Long-term Memory—0
Show:102550
← PrevPage 44 of 127Next →

Benchmark Results

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