Колногоров, А., Kolnogorov, A., Назин, А., Nazin, A., Шиян, Д. and Shiyan, D. (2021) “Two-armed bandit problem and batch version of the mirror descent algorithm”, Mathematical Game Theory and Applications, 13(2), pp. 9-39. doi: 10.17076/mgta_2021_2_34.