%0 Journal Article %A M. Goessel %A Yu. V. Popov %A V. G. Sragovich %T Adaptive control of partially observable Markov chains with rewards %J Doklady Akademii Nauk %D 1977 %P 767-769 %V 237 %N 4 %I mathdoc %U http://geodesic.mathdoc.fr/item/DAN_1977_237_4_a2/ %G ru %F DAN_1977_237_4_a2