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 331–340 of 1262 papers

TitleStatusHype
Data Acquisition for Improving Model Fairness using Reinforcement Learning—0
Data Dependent Regret Guarantees Against General Comparators for Full or Bandit Feedback—0
Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits—0
Data Poisoning Attacks in Contextual Bandits—0
Data Poisoning Attacks on Stochastic Bandits—0
DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees—0
Batched Nonparametric Bandits via k-Nearest Neighbor UCB—0
Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure—0
Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits—0
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making—0
Show:102550
← PrevPage 34 of 127Next →

Benchmark Results

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