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 701–710 of 1262 papers

TitleStatusHype
Online Meta-Learning in Adversarial Multi-Armed Bandits—0
Online Posterior Sampling with a Diffusion Prior—0
Online Residential Demand Response via Contextual Multi-Armed Bandits—0
Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints—0
Online Semi-Supervised Learning with Bandit Feedback—0
Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent—0
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling—0
On Minimax Optimal Offline Policy Evaluation—0
On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications—0
Towards Tractable Optimism in Model-Based Reinforcement Learning—0
Show:102550
← PrevPage 71 of 127Next →

Benchmark Results

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