Hamiltonian-Driven Adaptive Dynamic Programming for Nonlinear Discrete-Time Dynamic Systems
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.
Y. Yang et al., "Hamiltonian-Driven Adaptive Dynamic Programming for Nonlinear Discrete-Time Dynamic Systems," Proceedings of the 2017 International Joint Conference on Neural Networks (2017, Anchorage, AK), pp. 1339-1346, Institute of Electrical and Electronics Engineers (IEEE), May 2017.
The definitive version is available at https://doi.org/10.1109/IJCNN.2017.7966008
2017 International Joint Conference on Neural Networks, IJCNN (2017: May 14-19, Anchorage, AK)
Electrical and Computer Engineering
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)
International Standard Serial Number (ISSN)
Article - Conference proceedings
© 2017 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.