Nonparametric bandit methods
From MaRDI portal
The authors consider an infinite-horizon bandit problem within a nonparametric setting. Supposing K arms are available, each satisfying a probability bound, the sample plans proposed are shown to be asymptotically optimal and converge at guaranteed rates. In the bounded- arm case, the rate is optimal. Finally, the theory is extended to the case in which the bandit population is infinite.
Recommendations
- Bayesian nonparametric bandits
- Machine learning and nonparametric bandit theory
- The Nonstochastic Multiarmed Bandit Problem
- The multi-armed bandit problem: an efficient nonparametric solution
- Bandit algorithms
- A non-parametric solution to the multi-armed bandit problem with covariates
- Bandit convex optimization in non-stationary environments
- Nonstationary bandits with habituation and recovery dynamics
- Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates
Cites work
- A statistical foundation for machine learning, with application to Go- Moku
- Adaptive treatment allocation and the multi-armed bandit problem
- Asymptotically efficient adaptive allocation rules
- Bayesian nonparametric bandits
- Genetic Algorithms and the Optimal Allocation of Trials
- scientific article; zbMATH DE number 3168214 (Why is no real title available?)
- scientific article; zbMATH DE number 3856244 (Why is no real title available?)
- scientific article; zbMATH DE number 4078557 (Why is no real title available?)
- scientific article; zbMATH DE number 3310500 (Why is no real title available?)
- scientific article; zbMATH DE number 3418509 (Why is no real title available?)
- Probability Inequalities for Sums of Independent Random Variables
- Random Search in the Presence of Noise, with Application to Machine Learning
- Randomised allocation of treatments in sequential trials
- Some aspects of the sequential design of experiments
- Some One-Sided Theorems on the Tail Distribution of Sample Sums with Applications to the Last Time and Largest Excess of Boundary Crossings
- The uniform convergence of nearest neighbor regression function estimators and their application in optimization
Cited in
(22)- A decision model and methodology for the AIDS epidemic
- Machine learning for optimal blackjack counting strategies
- Strategy under the unknown stochastic environment: The nonparametric lop-pass problem
- The time until the final zero crossing of random sums with application to nonparametric bandit theory
- Nonparametric Bayesian multiarmed bandits for single-cell experiment design
- Bandit and covariate processes, with finite or non-denumerable set of arms
- The multi-armed bandit problem: an efficient nonparametric solution
- Learning vs earning trade-off with missing or censored observations: the two-armed Bayesian nonparametric beta-Stacy bandit problem
- Negatively Correlated Bandits
- Linearly parameterized bandits
- How Fast Is the Bandit?
- An asymptotically optimal policy for finite support models in the multiarmed bandit problem
- Sequential design with applications to the trim-loss problem
- Finite-time lower bounds for the two-armed bandit problem
- Pure exploration in infinitely-armed bandit models with fixed-confidence
- Machine learning and nonparametric bandit theory
- Nonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit models
- MULTI-ARMED BANDITS WITH COVARIATES:THEORY AND APPLICATIONS
- Infinite Arms Bandit: Optimality via Confidence Bounds
- Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criterion
- A non-parametric solution to the multi-armed bandit problem with covariates
- A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems
This page was built for publication: Nonparametric bandit methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q806690)
