Off-Policy Reinforcement Learning for Control Design

B Luo, HN Wu, T Huang - IEEE transactions on cybernetics, 2014‏ - ieeexplore.ieee.org
The H∞ control design problem is considered for nonlinear systems with unknown internal
system model. It is known that the nonlinear H∞ control problem can be transformed into …

Online solution of nonlinear two‐player zero‐sum games using synchronous policy iteration

KG Vamvoudakis, FL Lewis - International Journal of Robust …, 2012‏ - Wiley Online Library
The two‐player zero‐sum (ZS) game problem provides the solution to the bounded L2‐gain
problem and so is important for robust control. However, its solution depends on solving a …

Neural Network Based Online Simultaneous Policy Update Algorithm for Solving the HJI Equation in Nonlinear Control

HN Wu, B Luo - IEEE Transactions on Neural Networks and …, 2012‏ - ieeexplore.ieee.org
It is well known that the nonlinear H∞ state feedback control problem relies on the solution
of the Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential …

Enforcing robust control guarantees within neural network policies

PL Donti, M Roderick, M Fazlyab, JZ Kolter - arxiv preprint arxiv …, 2020‏ - arxiv.org
When designing controllers for safety-critical systems, practitioners often face a challenging
tradeoff between robustness and performance. While robust control methods provide …

Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm

D Liu, H Li, D Wang - Neurocomputing, 2013‏ - Elsevier
In this paper, we solve the zero-sum game problems for discrete-time affine nonlinear
systems with known dynamics via iterative adaptive dynamic programming algorithm. First, a …

Adaptive dynamic programming for online solution of a zero-sum differential game

D Vrabie, F Lewis - Journal of Control Theory and Applications, 2011‏ - Springer
This paper will present an approximate/adaptive dynamic programming (ADP) algorithm,
that uses the idea of integral reinforcement learning (IRL), to determine online the Nash …

Online solution of nonquadratic two‐player zero‐sum games arising in the H ∞  control of constrained input systems

H Modares, FL Lewis… - International Journal of …, 2014‏ - Wiley Online Library
In this paper, we present an online learning algorithm to find the solution to the H∞ control
problem of continuous‐time systems with input constraints. A suitable nonquadratic …

Nonlinear differential games-based impact-angle-constrained guidance law

R Bardhan, D Ghose - Journal of Guidance, Control, and Dynamics, 2015‏ - arc.aiaa.org
The problem of intercepting a maneuvering target at a prespecified impact angle is posed in
nonlinear zero-sum differential games framework. A feedback form solution is proposed by …

Online solution of two-player zero-sum games for continuous-time nonlinear systems with completely unknown dynamics

Y Fu, T Chai - IEEE transactions on neural networks and …, 2015‏ - ieeexplore.ieee.org
Regarding two-player zero-sum games of continuous-time nonlinear systems with
completely unknown dynamics, this paper presents an online adaptive algorithm for learning …

Real time control of tethered satellite systems to de-orbit space debris

P Razzaghi, E Al Khatib, S Bakhtiari… - Aerospace Science and …, 2021‏ - Elsevier
Abstract Space debris has become a huge concern for orbital missions that makes
remediation a critical and necessary action. Using Tethered Satellite System (TSS) to de …