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 376–400 of 1262 papers

TitleStatusHype
Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints—0
Distributed Online Learning via Cooperative Contextual Bandits—0
Distributed Optimization via Kernelized Multi-armed Bandits—0
Distributed Thompson Sampling—0
An Empirical Evaluation of Thompson Sampling—0
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits—0
Distributionally Robust Batch Contextual Bandits—0
Distribution-dependent and Time-uniform Bounds for Piecewise i.i.d Bandits—0
Distribution-Dependent Rates for Multi-Distribution Learning—0
Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience—0
Diversity-Based Recruitment in Crowdsensing By Combinatorial Multi-Armed Bandits—0
Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits—0
DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback—0
Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits—0
Online Multi-Armed Bandits with Adaptive Inference—0
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing—0
Bi-Criteria Optimization for Combinatorial Bandits: Sublinear Regret and Constraint Violation under Bandit Feedback—0
A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option—0
Doubly robust off-policy evaluation with shrinkage—0
Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy—0
Doubly Robust Policy Evaluation and Optimization—0
Boltzmann Exploration Done Right—0
Active Search for High Recall: a Non-Stationary Extension of Thompson Sampling—0
Adapting to Misspecification in Contextual Bandits—0
Dynamic Global Sensitivity for Differentially Private Contextual Bandits—0
Show:102550
← PrevPage 16 of 51Next →

Benchmark Results

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