Journal
OPTIMAL CONTROL APPLICATIONS & METHODS
Volume 38, Issue 3, Pages 317-335Publisher
WILEY
DOI: 10.1002/oca.2259
Keywords
adaptive dynamic programming; optimal control; discrete-time; nonlinear system; neural network; online learning; Lyapunov method
Categories
Funding
- National Natural Science Foundation of China [61233001, 61273140, 61304086, 61374105]
- Beijing Natural Science Foundation [4132078]
- Early Career Development Award of SKLMCCS
Ask authors/readers for more resources
In this paper, a novel identifier-actor-critic optimal control scheme is developed for discrete-time affine nonlinear systems with uncertainties. In contrast to traditional adaptive dynamic programming methodology, which requires at least partial knowledge of the system dynamics, a neural-network identifier is employed to learn the unknown control coefficient matrix working together with actor-critic-based scheme to solve the optimal control online. The critic network learns the approximate value function at each step. The actor network attempts to improve the current policy based on the approximate value function. The weights of all neural networks are updated at each sampling instant. Lyapunov theory is utilized to prove the stability of closed-loop system. It shows that system states and neural network weights are uniformly ultimately bounded. Finally, simulations are provided to illustrate the effectiveness of the developed method. Copyright (C) 2016 John Wiley & Sons, Ltd.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available