Title :
A model reference adaptive search method for stochastic optimization with applications to Markov decision processes
Author :
Hu, Jiaqiao ; Fu, Michael C. ; Marcus, Steven I.
Author_Institution :
State Univ. of New York, Stony Brook
Abstract :
We propose a randomized search method called stochastic model reference adaptive search (SMRAS) for solving stochastic optimization problems. We present its global convergence properties in a general stochastic setting, and explore its applications for solving Markov decision processes.
Keywords :
Markov processes; convergence; decision theory; optimisation; search problems; Markov decision processes; global convergence; randomized search method; stochastic model reference adaptive search; stochastic optimization; Adaptive control; Algorithm design and analysis; Convergence; Learning; Monte Carlo methods; Optimization methods; Programmable control; Random variables; Search methods; Stochastic processes;
Conference_Titel :
Decision and Control, 2007 46th IEEE Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
978-1-4244-1497-0
Electronic_ISBN :
0191-2216
DOI :
10.1109/CDC.2007.4434328