TY  - JOUR
AU  - Hernández-Lerma, Onésimo
TI  - Approximation and adaptive control of Markov processes: Average reward criterion
JO  - Kybernetika
PY  - 1987
SP  - 265
EP  - 288
VL  - 23
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/KYB_1987__23_4_a0/
LA  - en
ID  - KYB_1987__23_4_a0
ER  -