Awi Federgruen

“Discounted and undiscounted value-iteration in Markov decision processes: A survey”

Coauthor(s): Paul Schweitzer.

Editors: Martin L. Puterman

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.

Source: Dynamic Programming and its Applications
Exact Citation:
Federgruen, Awi, and P. J. Schweitzer. "Discounted and undiscounted value-iteration in Markov decision processes: A survey." In Dynamic Programming and its Applications, 23-53. Ed. Martin L. Puterman. Orlando, FL: Academic Press, 1979.
Pages: 23-53
Place: Orlando, FL
Date: 1979

Close Window