Title :
Approximate dynamic programming, local or global optimal solution?
Author :
Heydari, Ali ; Balakrishnan, Sivasubramanya N.
Author_Institution :
Mech. Eng. Dept., South Dakota Sch. of Mines & Technol., Rapid City, SD, USA
Abstract :
The problem of global optimality analysis of approximate dynamic programming based solutions is investigated in this study. Sufficient conditions for global optimality is obtained without requiring the state penalizing terms in the cost function or the functions representing the dynamics to be convex functions. Afterwards, the theoretical results are confirmed through a qualitative analysis of an example problem.
Keywords :
dynamic programming; optimal control; ADP; approximate dynamic programming; global optimality analysis; optimal control problems; Convex functions; Cost function; Dynamic programming; Equations; Least squares approximations; Optimal control; Learning; Neural networks; Optimal control;
Conference_Titel :
American Control Conference (ACC), 2014
Conference_Location :
Portland, OR
Print_ISBN :
978-1-4799-3272-6
DOI :
10.1109/ACC.2014.6859117
