Hamiltonian-Driven Adaptive Dynamic Programming for Nonlinear Discrete-Time Dynamic Systems

Abstract

In this paper, based on the Hamiltonian, an alternative interpretation about the iterative adaptive dynamic programming (ADP) approach from the perspective of optimization is developed for discrete time nonlinear dynamic systems. The role of the Hamiltonian in iterative ADP is explained. The resulting Hamiltonian driven ADP is able to evaluate the performance with respect to arbitrary admissible policies, compare two different admissible policies and further improve the given admissible policy. The convergence of the Hamiltonian ADP to the optimal policy is proven. Implementation of the Hamiltonian-driven ADP by neural networks is discussed based on the assumption that each iterative policy and value function can be updated exactly. Finally, a simulation is conducted to verify the effectiveness of the presented Hamiltonian-driven ADP.

Meeting Name

2017 International Joint Conference on Neural Networks, IJCNN (2017: May 14-19, Anchorage, AK)

Department(s)

Electrical and Computer Engineering

Research Center/Lab(s)

Center for High Performance Computing Research

Keywords and Phrases

Dynamical systems; Hamiltonians; Nonlinear dynamical systems; Adaptive dynamic programming; Discrete time; Nonlinear discrete-time; Optimal policies; Value functions; Dynamic programming

International Standard Book Number (ISBN)

978-1-5090-6182-2

International Standard Serial Number (ISSN)

2161-4407

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2017 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 May 2017

Link to Full Text

Share

 
COinS