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 201–210 of 1262 papers

TitleStatusHype
Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood MatchingCode0
Model selection for contextual banditsCode0
Cascading Bandits for Large-Scale Recommendation ProblemsCode0
Combinatorial Bandits under Strategic ManipulationsCode0
Constrained regret minimization for multi-criterion multi-armed banditsCode0
Off-Policy Evaluation Using Information Borrowing and Context-Based SwitchingCode0
Online Matching: A Real-time Bandit System for Large-scale RecommendationsCode0
Budgeted Multi-Armed Bandits with Asymmetric Confidence IntervalsCode0
On Private Online Convex Optimization: Optimal Algorithms in _p-Geometry and High Dimensional Contextual BanditsCode0
Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson SamplingCode0
Show:102550
← PrevPage 21 of 127Next →

Benchmark Results

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