Visible to the public Hamiltonian-driven adaptive dynamic programming for nonlinear discrete-time dynamic systems

TitleHamiltonian-driven adaptive dynamic programming for nonlinear discrete-time dynamic systems
Publication TypeConference Paper
Year of Publication2017
AuthorsYang, Y., Wunsch, D., Yin, Y.
Conference Name2017 International Joint Conference on Neural Networks (IJCNN)
Keywordscomposability, discrete time nonlinear dynamic systems, discrete time systems, Discrete-time systems, dynamic programming, Dynamical Systems, Hamiltonian-driven adaptive dynamic programming, Hamiltonian-driven ADP, iterative adaptive dynamic programming, iterative ADP, iterative policy, Linear programming, Mathematical model, Metrics, Neural networks, neurocontrollers, nonlinear control systems, nonlinear discrete-time dynamic systems, Nonlinear dynamical systems, optimal control, optimal policy, Optimization, pubcrawl, resilience, Resiliency, value function

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.

Citation Keyyang_hamiltonian-driven_2017