The convergence of value iteration in average cost Markov decision chains.

Linn I. Sennott

Published in: Oper. Res. Lett. (1996)

Keyphrases

markov decision chains
average cost
markov decision processes
long run
finite state
risk sensitive
optimal control
optimal policy
finite number
convergence rate
infinite horizon
total cost
linear program
linear programming
stationary policies
finite horizon
special case
inventory models