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 521–530 of 1262 papers

TitleStatusHype
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees—0
Data Poisoning Attacks on Stochastic Bandits—0
Batched Nonparametric Bandits via k-Nearest Neighbor UCB—0
Regret Bounds for Batched Bandits—0
A Model Selection Approach for Corruption Robust Reinforcement Learning—0
Data Poisoning Attacks in Contextual Bandits—0
Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits—0
Data Dependent Regret Guarantees Against General Comparators for Full or Bandit Feedback—0
Data Acquisition for Improving Model Fairness using Reinforcement Learning—0
Batched Coarse Ranking in Multi-Armed Bandits—0
Show:102550
← PrevPage 53 of 127Next →

Benchmark Results

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