Bernoulli multi-armed bandit problem under delayed feedback

Тип публікації :
Стаття
Дата випуску :
2021
Автор(и) :
Dzhoha, A. S.
Мова основного тексту :
Англійська
eKNUTSHIR URL :
DOI :
Журнал :
Випуск :
1
ISSN :
1812-5409
Початкова сторінка :
20
Кінцева сторінка :
26
Цитування :
[APA 7] Dzhoha, A. S. (2021). Bernoulli multi-armed bandit problem under delayed feedback. Bulletin of Taras Shevchenko National University of Kyiv. Physics and Mathematics, (1), 20–26. https://doi.org/10.17721/1812-5409.2021/1.2
[ДСТУ] Dzhoha A. S. Bernoulli multi-armed bandit problem under delayed feedback. Bulletin of Taras Shevchenko National University of Kyiv. Physics and Mathematics. 2021. no. 1. P. 20—26. DOI: 10.17721/1812-5409.2021/1.2 (date of access: 25.07.2026).
Online learning under delayed feedback has been recently gaining increasing attention. Learning with delays is more natural in most practical applications since the feedback from the environment is not immediate. For example, the response to a drug in clinical trials could take a while. In this paper, we study the multi-armed bandit problem with Bernoulli distribution in the environment with delays by evaluating the Explore-First algorithm. We obtain the upper bounds of the algorithm, the theoretical results are applied to develop the software framework for conducting numerical experiments.
Pages of the article in the issue: 20 - 26
Language of the article: English
Файл(и) :
Вантажиться...
Ескіз
Завантажити
Формат :

Adobe PDF

Розмір :

418.83 KB

Контрольна сума :

(MD5):718a3b541c261885ccbbb7501edd6255

Creative Commons Attribution 4.0 International
Якщо не вказано інше, ця робота розповсюджується на умовах ліцензії Creative Commons Attribution 4.0 International