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 811–820 of 1262 papers

TitleStatusHype
Multi-armed Bandits with Cost Subsidy—0
Towards Fundamental Limits of Multi-armed Bandits with Random Walk Feedback—0
On No-Sensing Adversarial Multi-player Multi-armed Bandits with Collision Communications—0
Multi-Armed Bandits with Censored Consumption of Resources—0
Resource Allocation in Multi-armed Bandit Exploration: Overcoming Sublinear Scaling with Adaptive Parallelism—0
Learning to Actively Learn: A Robust Approach—0
Tractable contextual bandits beyond realizability—0
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards—0
Online Semi-Supervised Learning with Bandit Feedback—0
Online Algorithm for Unsupervised Sequential Selection with Contextual Information—0
Show:102550
← PrevPage 82 of 127Next →

Benchmark Results

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