Neurodynamic Programming and Zero-Sum Games for Constrained Control Systems

@article{AbuKhalaf2008NeurodynamicPA,
  title={Neurodynamic Programming and Zero-Sum Games for Constrained Control Systems},
  author={Murad Abu-Khalaf and Frank L. Lewis and Jie Huang},
  journal={IEEE Transactions on Neural Networks},
  year={2008},
  volume={19},
  pages={1243-1252}
}
In this paper, neural networks are used along with two-player policy iterations to solve for the feedback strategies of a continuous-time zero-sum game that appears in L2-gain optimal control, suboptimal Hinfin control, of nonlinear systems affine in input with the control policy having saturation constraints. The result is a closed-form representation, on a prescribed compact set chosen a priori, of the feedback strategies and the value function that solves the associated Hamilton-Jacobi… Expand
Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP
TLDR
The novel weight tuning laws for critic neural networks are proposed, which not only ensure the Nash equilibrium to be reached but also guarantee the system to be stable and demonstrate the uniform ultimate boundedness of the closed-loop system. Expand
Constrained online optimal control for continuous-time nonlinear systems using neuro-dynamic programming
TLDR
An online adaptive optimal control scheme to solve the infinite-horizon optimal control problem of continuous-time nonlinear systems with control constraints by using only a critic neural network to derive the optimal control instead of typical action-critic dual networks employed in neuro-dynamic programming methods. Expand
An Approximate Control Algorithm for Zero-Sum Differential Games Using Adaptive Critic Technique
TLDR
A novel adaptive dynamic programming (ADP) algorithm is proposed to approximate the optimal value function through a critic neural network (NN) to obtain the approximate optimal control policy and the worst-base disturbance policy. Expand
Zero-sum differential games for nonlinear systems using adaptive dynamic programming with input constraint
In this paper, the zero-sum differential game problem for a class of nonlinear system with input constraints is investigated via adaptive dynamic programming (ADP). A suitable non-quadraticExpand
Adaptive dynamic programming for H∞ control of constrained-input nonlinear systems
This paper presents a novel adaptive/approximate dynamic programming algorithm to solve the H∞ control problem of constrained-input continuous-time nonlinear systems. The developed algorithm employsExpand
Robust control design for multi-player nonlinear systems with input disturbances via adaptive dynamic programming
TLDR
It is proved that the robust control strategy can guarantee the multi-player nonlinear systems to be stable in the sense of uniform ultimate boundedness (UUB) with disturbance rejection. Expand
Integral Reinforcement Learning for Linear Continuous-Time Zero-Sum Games With Completely Unknown Dynamics
TLDR
An integral reinforcement learning algorithm based on policy iteration to learn online the Nash equilibrium solution for a two-player zero-sum differential game with completely unknown linear continuous-time dynamics is developed. Expand
Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm
TLDR
A greedy heuristic dynamic programming iteration algorithm is developed to solve the zero-sum game problems, which can be used to solves the Hamilton-Jacobi-Isaacs equation associated with H"~ optimal regulation control problems. Expand
Adaptive near-optimal neuro controller for continuous-time nonaffine nonlinear systems with constrained input
TLDR
By employing two Neural Networks (NNs), the solution of Hamilton-Jacobi-Bellman (HJB) equation associated with the cost function is derived without requiring a priori knowledge about system dynamics. Expand
Model-Free Adaptive Control for Unknown Nonlinear Zero-Sum Differential Game
TLDR
The online learning algorithm is proposed based on the GDHP method to solve the Hamilton–Jacobi–Isaacs equation associated with optimal regulation control problem and three neural networks are established to approximate the optimal saddle point feedback control law, the disturbance law, and the performance index. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach
TLDR
It is shown that the constrained optimal control law has the largest region of asymptotic stability (RAS) and the result is a nearly optimal constrained state feedback controller that has been tuned a priori off-line. Expand
Policy Iterations on the Hamilton–Jacobi–Isaacs Equation for $H_{\infty}$ State Feedback Control With Input Saturation
An Hinfin suboptimal state feedback controller for constrained input systems is derived using the Hamilton-Jacobi-Isaacs (HJI) equation of a corresponding zero-sum game that uses a special quasi-normExpand
Neural approximations for infinite-horizon optimal control of nonlinear stochastic systems
TLDR
Simulation results show that the proposed feedback control law may constitute an effective tool for solving a wide class of control problems traditionally regarded as difficult ones, to a sufficient degree of accuracy. Expand
H∞-0ptimal Control and Related Minimax Design Problems: A Dynamic Game Approach
TLDR
The authors believe that the H-infinity-optimal control theory is now at a stage where it can easily be incorporated into a second-level graduate course in a control curriculum, that would follow a basic course in linear control theory covering LQ and LQG designs. Expand
A preliminary control design for the nonlinear benchmark problem
  • C. Mracek, J. Cloutier
  • Computer Science
  • Proceeding of the 1996 IEEE International Conference on Control Applications IEEE International Conference on Control Applications held together with IEEE International Symposium on Intelligent Contro
  • 1996
TLDR
Analysis of the design shows that in the absence of disturbances and uncertainties, the SDRE nonlinear feedback solution compares very favorably to the optimal open-loop solution obtained via numerical optimization. Expand
Role of performance functionals in control laws design
  • S. Lyshevski
  • Mathematics
  • Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148)
  • 2001
The research in optimal control has been concentrated on design of control laws in order to optimize the dynamic performance of systems. These optimization problems were explicitly formulated andExpand
Adaptively controlling nonlinear continuous-time systems using multilayer neural networks
TLDR
Multilayer neural networks are used in a nonlinear adaptive control problem to control the plant to track a reference command and a local convergence result is provided, which says that if the initial parameter errors are small enough, then the tracking error will converge to a bounded area. Expand
Stable adaptive neural control scheme for nonlinear systems
TLDR
A design methodology is developed that expands the class of nonlinear systems that adaptive neural control schemes can be applied to and relaxes some of the restrictive assumptions that are usually made. Expand
Stable Adaptive Neural Network Control
While neural network control has been successfully applied in various practical applications, many important issues, such as stability, robustness, and performance, have not been extensivelyExpand
Output feedback control of nonlinear systems using RBF neural networks
TLDR
An adaptive output feedback control scheme for the output tracking of a class of continuous-time nonlinear plants is presented and it is shown that by using adaptive control in conjunction with robust control, it is possible to tolerate larger approximation errors resulting from the use of lower order networks. Expand
...
1
2
3
4
5
...