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 191–200 of 1262 papers

TitleStatusHype
Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions—0
An Adaptive Method for Contextual Stochastic Multi-armed Bandits with Rewards Generated by a Linear Dynamical System—0
Linear Contextual Bandits with Hybrid Payoff: RevisitedCode0
Towards Domain Adaptive Neural Contextual Bandits—0
A Federated Online Restless Bandit Framework for Cooperative Resource Allocation—0
Asymptotically Optimal Regret for Black-Box Predict-then-Optimize—0
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning—0
A conversion theorem and minimax optimality for continuum contextual bandits—0
Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits—0
Adaptively Learning to Select-Rank in Online Platforms—0
Show:102550
← PrevPage 20 of 127Next →

Benchmark Results

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