The value iteration method for countable state Markov decision processes.

Yossi Aviv Awi Federgruen

Published in: Oper. Res. Lett. (1999)

Keyphrases

markov decision processes
state space
dynamic programming
finite state
optimal policy
transition matrices
policy iteration
search algorithm
fixed point
action space
objective function
least squares
decision theoretic planning
model based reinforcement learning
interval estimation