@article{TVP_2019_64_1_a3,
     author = {D. B. Rokhlin},
     title = {$Q$-learning in a stochastic {Stackelberg} game between an uninformed leader and a naive follower},
     journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
     pages = {53--74},
     year = {2019},
     volume = {64},
     number = {1},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TVP_2019_64_1_a3/}
}