MATHEMATICS

Adaptive control of partially observable Markov chains with rewards

M. Goessel^a, Yu. V. Popov^b, V. G. Sragovich<sup>b

a</sup> Central Institute of Cybernetics Academy of Sciences of the GDR, Berlin
^b Computing Centre, USSR Academy of Sciences, Moscow

UDC: 519.21

Presented: A. A. Dorodnitsyn
Received: 22.06.1977

Bibliographic databases:

• 
•