Journal ArticleDOI
Data-Driven Robust Control of Discrete-Time Uncertain Linear Systems via Off-Policy Reinforcement Learning
TLDR
A model-free solution to the robust stabilization problem of discrete-time linear dynamical systems with bounded and mismatched uncertainty is presented and it is shown that the optimal controller obtained by solving the ARE can robustly stabilize the uncertain system.Abstract:
This paper presents a model-free solution to the robust stabilization problem of discrete-time linear dynamical systems with bounded and mismatched uncertainty. An optimal controller design method is derived to solve the robust control problem, which results in solving an algebraic Riccati equation (ARE). It is shown that the optimal controller obtained by solving the ARE can robustly stabilize the uncertain system. To develop a model-free solution to the translated ARE, off-policy reinforcement learning (RL) is employed to solve the problem in hand without the requirement of system dynamics. In addition, the comparisons between on- and off-policy RL methods are presented regarding the robustness to probing noise and the dependence on system dynamics. Finally, a simulation example is carried out to validate the efficacy of the presented off-policy RL approach.read more
Citations
More filters
Journal ArticleDOI
Adaptive optimization algorithm for nonlinear Markov jump systems with partial unknown dynamics
TL;DR: An online adaptive optimal control problem for a class of nonlinear Markov jump systems (MJSs) is studied and a new online policy iteration algorithm is put forward to obtain the adaptive optimal controller.
Journal ArticleDOI
Online Barrier-Actor-Critic Learning for H∞ Control with Full-State Constraints and Input Saturation
TL;DR: A novel barrier-actor-critic algorithm is presented for adaptive optimal learning while guaranteeing the full-state constraints and input saturation and it is proven that the closed-loop signals remain bounded during the online learning phase.
Journal ArticleDOI
Safe Intermittent Reinforcement Learning With Static and Dynamic Event Generators
TL;DR: This article develops a barrier function-based system transformation to impose state constraints while converting the original problem to an unconstrained optimization problem and leverages an actor/critic structure to solve the problem online while guaranteeing optimality, stability, and safety.
Journal ArticleDOI
Safe reinforcement learning for dynamical games
Journal ArticleDOI
Hamiltonian-Driven Hybrid Adaptive Dynamic Programming
TL;DR: This article presents a model-based hybrid adaptive dynamic programming (ADP) framework consisting of continuous feedback-based policy evaluation and policy improvement steps as well as an intermittent policy implementation procedure that results in an intermittent ADP with a quantifiable performance and guaranteed closed-loop stability of the equilibrium point.
References
More filters
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Book
Matrix Analysis
Roger A. Horn,Charles R. Johnson +1 more
TL;DR: In this article, the authors present results of both classic and recent matrix analyses using canonical forms as a unifying theme, and demonstrate their importance in a variety of applications, such as linear algebra and matrix theory.
Journal ArticleDOI
Technical Note : \cal Q -Learning
Chris Watkins,Peter Dayan +1 more
TL;DR: This paper presents and proves in detail a convergence theorem forQ-learning based on that outlined in Watkins (1989), showing that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.
Book
Essentials of Robust Control
Kemin Zhou,John Doyle +1 more
TL;DR: In this article, the authors introduce linear algebraic Riccati Equations and linear systems with Ha spaces and balance model reduction, and Ha Loop Shaping, and Controller Reduction.