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 1–25 of 1262 papers

TitleStatusHype
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior ModelCode2
Off-Policy Evaluation for Large Action Spaces via EmbeddingsCode2
Hypothesis Generation with Large Language ModelsCode2
Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless BanditsCode1
Hierarchical Adaptive Contextual Bandits for Resource Constraint based RecommendationCode1
In-Context Reinforcement Learning for Variable Action SpacesCode1
Deep Bandits Show-Off: Simple and Efficient Exploration with Deep NetworksCode1
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed BanditsCode1
Carousel Personalization in Music Streaming Apps with Contextual BanditsCode1
Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous NetworksCode1
Federated Multi-Armed BanditsCode1
Generalized Linear Bandits with Local Differential PrivacyCode1
An empirical evaluation of active inference in multi-armed banditsCode1
Implicitly normalized forecaster with clipping for linear and non-linear heavy-tailed multi-armed banditsCode1
A Modern Introduction to Online LearningCode1
Anytime-valid off-policy inference for contextual banditsCode1
Balans: Multi-Armed Bandits-based Adaptive Large Neighborhood Search for Mixed-Integer Programming ProblemCode1
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed BanditsCode1
A unifying framework for generalised Bayesian online learning in non-stationary environmentsCode1
Competing for Shareable Arms in Multi-Player Multi-Armed BanditsCode1
Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions ModelingCode1
Discovering Minimal Reinforcement Learning EnvironmentsCode1
Efficient Contextual Bandits with Continuous ActionsCode1
Equitable Restless Multi-Armed Bandits: A General Framework Inspired By Digital HealthCode1
EE-Net: Exploitation-Exploration Neural Networks in Contextual BanditsCode1
Show:102550
← PrevPage 1 of 51Next →

Benchmark Results

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