Stochastic control in discrete time and applications to the theory of production

Author(s):  
A. Bensoussan
Author(s):  
Giordano Pola ◽  
Costanzo Manes ◽  
Arjan J. van der Schaft ◽  
Maria Domenica Di Benedetto

2012 ◽  
Vol 18 (6) ◽  
pp. 528-538 ◽  
Author(s):  
Xianping Guo ◽  
Adrián Hernández-del-Valle ◽  
Onésimo Hernández-Lerma

2000 ◽  
Vol 14 (2) ◽  
pp. 243-258 ◽  
Author(s):  
V. S. Borkar

A simulation-based algorithm for learning good policies for a discrete-time stochastic control process with unknown transition law is analyzed when the state and action spaces are compact subsets of Euclidean spaces. This extends the Q-learning scheme of discrete state/action problems along the lines of Baker [4]. Almost sure convergence is proved under suitable conditions.


Sign in / Sign up

Export Citation Format

Share Document