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 1251–1262 of 1262 papers

TitleStatusHype
An Empirical Evaluation of Thompson Sampling—0
From Bandits to Experts: On the Value of Side-Observations—0
Multi-armed bandits on implicit metric spaces—0
PAC-Bayesian Analysis of Contextual Bandits—0
Dynamic Pricing with Limited Supply—0
Doubly Robust Policy Evaluation and LearningCode0
Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards—0
Contextual Bandits with Similarity Information—0
Mortal Multi-Armed Bandits—0
Multi-Armed Bandits in Metric Spaces—0
Learning diverse rankings with multi-armed bandits—0
The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information—0
Show:102550
← PrevPage 26 of 26Next →

Benchmark Results

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