Колногоров, Александр, Alexander Kolnogorov, Александр Назин, Alexander Nazin, Дмитрий Шиян, and Dmitry Shiyan. 2021. “Two-Armed Bandit Problem and Batch Version of the Mirror Descent Algorithm”. Mathematical Game Theory and Applications 13 (2), 9-39. https://doi.org/10.17076/mgta_2021_2_34.