Колногоров, А., A. Kolnogorov, А. Назин, A. Nazin, Д. Шиян, and D. Shiyan. “Two-Armed Bandit Problem and Batch Version of the Mirror Descent Algorithm”. Mathematical Game Theory and Applications, Vol. 13, no. 2, Oct. 2021, pp. 9-39, doi:10.17076/mgta_2021_2_34.