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 1121–1130 of 1262 papers

TitleStatusHype
Asymptotic Convergence of Thompson Sampling—0
Asymptotic Instance-Optimal Algorithms for Interactive Decision Making—0
Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits—0
Asymptotic Randomised Control with applications to bandits—0
Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis—0
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning—0
Automatic Ensemble Learning for Online Influence Maximization—0
AutoML for Contextual Bandits—0
Autonomous Drug Design with Multi-Armed Bandits—0
Balanced Linear Contextual Bandits—0
Show:102550
← PrevPage 113 of 127Next →

Benchmark Results

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