Model-Free Dual Heuristic Dynamic Programming

• Published in: IEEE transaction on neural networks and learning systems Vol. 26; no. 8; pp. 1834 - 1839
• Main Authors: Zhen Ni, Haibo He, Xiangnan Zhong, Prokhorov, Danil V.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2015
• Subjects: Action-dependent dual heuristic dynamic programming (DHP); adaptive critic designs (ACDs); adaptive dynamic programming (ADP); Approximation methods; Computational modeling; Convergence; Dynamic programming; Learning systems; Linear programming; Mathematical model; online learning; reinforcement learning; adaptive critic designs (ACDs); Action-dependent dual heuristic dynamic programming (DHP); adaptive dynamic programming (ADP); online learning; reinforcement learning
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2015.2424971

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.