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

Showing 11511160 of 1262 papers

TitleStatusHype
Finding All ε-Good Arms in Stochastic BanditsCode0
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit FeedbackCode0
Let's Get It Started: Fostering the Discoverability of New Releases on DeezerCode0
Ranking In Generalized Linear BanditsCode0
Myopic Bayesian Design of Experiments via Posterior Sampling and Probabilistic ProgrammingCode0
Finite-time Analysis of Globally Nonstationary Multi-Armed BanditsCode0
Online Limited Memory Neural-Linear Bandits with Likelihood MatchingCode0
Online Matching: A Real-time Bandit System for Large-scale RecommendationsCode0
Thompson Sampling for Contextual Bandits with Linear PayoffsCode0
Semiparametric Contextual BanditsCode0
Show:102550
← PrevPage 116 of 127Next →

Benchmark Results

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