Bandit problems with infinitely many arms
From MaRDI portal
Publication:1374228
DOI10.1214/aos/1069362389zbMath0881.62083MaRDI QIDQ1374228
David C. Heath, Robert W. Chen, Alan Zame, Donald A. Berry, Lawrence A. Shepp
Publication date: 22 February 1998
Published in: The Annals of Statistics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1214/aos/1069362389
bandit problem; dynamic allocation of Bernoulli processes; sequential experimentation; staying with a winner; switching with a loser
62L05: Sequential statistical design
60F99: Limit theorems in probability theory
62C25: Compound decision problems in statistical decision theory
Related Items
Infinite Arms Bandit: Optimality via Confidence Bounds, Satisficing in Time-Sensitive Bandit Learning, Topp-Leone distribution with an application to binomial sampling, Optimal Bayesian strategies for the infinite-armed Bernoulli bandit, A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions, Randomized allocation with nonparametric estimation for a multi-armed bandit problem with covariates, Bandit and covariate processes, with finite or non-denumerable set of arms, Ballooning multi-armed bandits, Two-Armed Bandit Strategies that Discount Past and Future