Model-Free Dual Heuristic Dynamic Programming
Document Type
Article
Date of Original Version
8-1-2015
Abstract
Model-based dual heuristic dynamic programming (MB-DHP) is a popular approach in approximating optimal solutions in control problems. Yet, it usually requires offline training for the model network, and thus resulting in extra computational cost. In this brief, we propose a model-free DHP (MF-DHP) design based on finite-difference technique. In particular, we adopt multilayer perceptron with one hidden layer for both the action and the critic networks design, and use delayed objective functions to train both the action and the critic networks online over time. We test both the MF-DHP and MB-DHP approaches with a discrete time example and a continuous time example under the same parameter settings. Our simulation results demonstrate that the MF-DHP approach can obtain a control performance competitive with that of the traditional MB-DHP approach while requiring less computational resources.
Publication Title, e.g., Journal
IEEE Transactions on Neural Networks and Learning Systems
Volume
26
Issue
8
Citation/Publisher Attribution
Ni, Zhen, Haibo He, Xiangnan Zhong, and Danil V. Prokhorov. "Model-Free Dual Heuristic Dynamic Programming." IEEE Transactions on Neural Networks and Learning Systems 26, 8 (2015): 1834-1839. doi: 10.1109/TNNLS.2015.2424971.