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 351–375 of 1262 papers

TitleStatusHype
Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling—0
Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing—0
Adversarial Attacks on Combinatorial Multi-Armed BanditsCode0
Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation—0
Improved Algorithms for Adversarial Bandits with Unbounded Losses—0
Adversarial Contextual Bandits Go Kernelized—0
Discrete Choice Multi-Armed Bandits—0
Bayesian Design Principles for Frequentist Sequential LearningCode0
Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts—0
Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience—0
A Convex Framework for Confounding Robust InferenceCode0
Task Selection and Assignment for Multi-modal Multi-task Dialogue Act Classification with Non-stationary Multi-armed Bandits—0
Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits—0
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing—0
The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits—0
Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits—0
Concentrated Differential Privacy for Bandits—0
Stochastic Graph Bandit Learning with Side-Observations—0
Pure Exploration under Mediators' Feedback—0
Learning How to Price Charging in Electric Ride-Hailing Markets—0
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity ConstraintsCode0
On Universally Optimal Algorithms for A/B Testing—0
Clustered Linear Contextual Bandits with Knapsacks—0
Graph Neural Bandits—0
Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit ApproachCode0
Show:102550
← PrevPage 15 of 51Next →

Benchmark Results

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