Multi-Armed Bandit Problem and Batch UCB Rule
From MaRDI portal
Publication:6313409
arXiv1902.00214MaRDI QIDQ6313409FDOQ6313409
Authors: Alex V. Kolnogorov, S. V. Garbar 
Publication date: 1 February 2019
Abstract: We obtain the upper bound of the loss function for a strategy in the multi-armed bandit problem with Gaussian distributions of incomes. Considered strategy is an asymptotic generalization of the strategy proposed by J. Bather for the multi-armed bandit problem and using UCB rule, i.e. choosing the action corresponding to the maximum of the upper bound of the confidence interval of the current estimate of the expected value of one-step income. Results are obtained with the help of invariant description of the control on the unit horizon in the domain of close distributions because just there the loss function attains its maximal values. UCB rule is widely used in machine learning. It can be also used for the batch data processing optimization if there are two alternative processing methods available with different a priori unknown efficiencies.
Minimax procedures in statistical decision theory (62C20) Robustness and adaptive procedures (parametric inference) (62F35) Stochastic learning and adaptive control (93E35)
This page was built for publication: Multi-Armed Bandit Problem and Batch UCB Rule
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6313409)
