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 951–960 of 1262 papers

TitleStatusHype
The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits—0
Are sample means in multi-armed bandits positively or negatively biased?—0
Cramming Contextual Bandits for On-policy Statistical Evaluation—0
The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information—0
The Externalities of Exploration and How Data Diversity Helps Exploitation—0
The K-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates—0
The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication—0
The Pareto Frontier of model selection for general Contextual Bandits—0
The Price of Differential Privacy For Online Learning—0
Thompson Sampling for Budgeted Multi-armed Bandits—0
Show:102550
← PrevPage 96 of 127Next →

Benchmark Results

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