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 31–40 of 1262 papers

TitleStatusHype
Neural Contextual Bandits Under Delayed Feedback Constraints—0
On the Problem of Best Arm Retention—0
Learning-Based User Association for MmWave Vehicular Networks With Kernelized Contextual Bandits—0
Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making—0
A Classification View on Meta Learning Bandits—0
An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System—0
Antithetic Sampling for Top-k Shapley IdentificationCode0
Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries—0
Reinforcement Learning for Machine Learning Model Deployment: Evaluating Multi-Armed Bandits in ML Ops Environments—0
MultiScale Contextual Bandits for Long Term Objectives—0
Show:102550
← PrevPage 4 of 127Next →

Benchmark Results

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