A pause control approach to the value iteration scheme in average Markov decision processes

Rolando Cavazos-Cadena، نويسنده ,

ماهنامه با شماره پیاپی سال 1998

11

209

219

Long-run average cost criterion , Lyapunov function condition , Controlled Markov chains , Artificial action , Convergent approximatiיJnsto the solution of the optimality equation

Systems and Control Letters

1998

Systems and Control Letters

141469