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 976–1000 of 1262 papers

TitleStatusHype
NeuralUCB: Contextual Bandits with Neural Network-Based Exploration—0
Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood MatchingCode0
Learning Effective Exploration Strategies For Contextual Bandits—0
Practical Calculation of Gittins Indices for Multi-armed BanditsCode0
AutoML for Contextual Bandits—0
Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret RegimesCode0
Censored Semi-Bandits: A Framework for Resource Allocation with Censored FeedbackCode0
A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits—0
Nonparametric Contextual Bandits in an Unknown Metric Space—0
Doubly-Robust Lasso BanditCode0
Scaling Multi-Armed Bandit Algorithms—0
Doubly robust off-policy evaluation with shrinkage—0
Parameterized Exploration—0
Productization Challenges of Contextual Multi-Armed Bandits—0
Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits—0
Exploration Through Reward Biasing: Reward-Biased Maximum Likelihood Estimation for Stochastic Multi-Armed Bandits—0
Multi-Armed Bandits with Fairness Constraints for Distributing Resources to Human Teammates—0
Bayesian Optimisation over Multiple Continuous and Categorical InputsCode0
Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules—0
Online Allocation and Pricing: Constant Regret via Bellman Inequalities—0
Competing Bandits in Matching Markets—0
Bootstrapping Upper Confidence Bound—0
Beam Learning -- Using Machine Learning for Finding Beam Directions—0
Stochastic Neural Network with Kronecker Flow—0
Balanced off-policy evaluation in general action spaces—0
Show:102550
← PrevPage 40 of 51Next →

Benchmark Results

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