*two-armed bandit problem, minimax approach, mirror descent algorithm, EXP3, batch processing*

Publications

# Scientific publications

А.В. Колногоров, А.В. Назин, Д.Н. Шиян.

Задача о двуруком бандите и пакетная версия алгоритма зеркального спуска

// Математическая Теория Игр и ее Приложения, т. 13, в. 2. 2021. C. 9-39

Keywords:

We consider the minimax setup for the two-armed bandit problem as applied to data processing if there are two alternative processing methods with different a priori unknown efficiencies. One should determine the most efficient method and provide its predominant application. To this end, we use the mirror descent algorithm (MDA). It is well-known that corresponding minimax risk has the order of N1=2 with N being the number of processed data and this bound is unimprovable in order. We propose a batch version of the MDA which allows processing data by packets that is especially important if parallel data processing can be provided. In this case, the processing time is determined by the number of batches rather than by the total number of data. Unexpectedly, it turned out that the batch version behaves unlike the ordinary one even if the number of packets is large. Moreover, the batch version provides significantly smaller value of the minimax risk, i.e., it considerably improves a control performance. We explain this result by considering another batch modification of the MDA which behavior is close to behavior of the ordinary version and minimax risk is close as well. Our estimates use invariant descriptions of the algorithms based on Gaussian approximations of incomes in batches of data in the domain of "close" distributions and are obtained by Monte-Carlo simulations.

**Indexed at**RSCI, RSCI (WS)

vol13_2_009_kolnogorov.pdf (383 Kb, total downloads: 63)

Last modified: October 26, 2021