Abstract
A survey is given of the present state of the art of value-iteration and related successive approximation methods, as well as of resulting turnpike properties, in both the discounted and undiscounted version of finite state and action Markov Decision Problems.
Full Citation
.
“Discounted and undiscounted value-iteration in Markov decision processes: A survey.”
In
Dynamic Programming and its Applications
,
edited by ,
23
-53
.
Orlando, FL
:
Academic Press
,
1979.