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 561–570 of 1262 papers

TitleStatusHype
Provably and Practically Efficient Neural Contextual Bandits—0
Provable General Function Class Representation Learning in Multitask Bandits and MDPs—0
Online Meta-Learning in Adversarial Multi-Armed Bandits—0
Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets—0
Optimistic Whittle Index Policy: Online Learning for Restless BanditsCode0
Federated Neural BanditsCode0
Meta-Learning Adversarial Bandits—0
Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits—0
Fairness and Welfare Quantification for Regret in Multi-Armed Bandits—0
Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment—0
Show:102550
← PrevPage 57 of 127Next →

Benchmark Results

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