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 351–360 of 1262 papers

TitleStatusHype
Byzantine-Resilient Decentralized Multi-Armed Bandits—0
Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing—0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Improved Algorithms for Adversarial Bandits with Unbounded Losses—0
Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation—0
Adversarial Contextual Bandits Go Kernelized—0
Bayesian Design Principles for Frequentist Sequential LearningCode0
Discrete Choice Multi-Armed Bandits—0
Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience—0
Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts—0
Show:102550
← PrevPage 36 of 127Next →

Benchmark Results

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