Abstract
The problem of global optimality analysis of approximate dynamic programming-based solutions is investigated in this study. Sufficient conditions for global optimality are 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. © 2014 American Automatic Control Council.
Recommended Citation
A. Heydari and S. N. Balakrishnan, "Approximate Dynamic Programming, Local or Global Optimal Solution?," Proceedings of the American Control Conference, pp. 1237 - 1242, article no. 6859117, Institute of Electrical and Electronics Engineers, Jan 2014.
The definitive version is available at https://doi.org/10.1109/ACC.2014.6859117
Department(s)
Mechanical and Aerospace Engineering
Keywords and Phrases
Learning; Neural networks; Optimal control
International Standard Book Number (ISBN)
978-147993272-6
International Standard Serial Number (ISSN)
0743-1619
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2014
