TY  - JOUR
AU  - Lorenzo Magán, José María
PY  - 2010
DO  - 10.1109/TAC.2009.2033848
SN  - 0018-9286
UR  - https://hdl.handle.net/20.500.14352/108643
T2  - IEEE TRANSACTIONS ON AUTOMATIC CONTROL
AB  - We study the approximation of an ergodic average reward continuous-time denumerable state Markov decision process (MDP) by means of a sequence of MDPs. Our results include the convergence of the corresponding optimal policies and the optimal gains....
LA  - eng
M2  - 201
PB  - IEEE
KW  - Approximation of control problems
KW  - Ergodic Markov decision processes (MDPs)
KW  - Policy iteration algorithm
TI  - Approximating ergodic average reward continuous: time controlled Markov chains
TY  - journal article
VL  - 55
ER  -