Колногоров, Александр, Alexander Kolnogorov, Александр Назин, Alexander Nazin, Дмитрий Шиян, and Dmitry Shiyan. “Two-Armed Bandit Problem and Batch Version of the Mirror Descent Algorithm”. Mathematical Game Theory and Applications 13, no. 2 (October 20, 2021): 9-39. Accessed May 14, 2025. http://mgta.krc.karelia.ru/ojs/index.php/mgta/article/view/34.