Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics

By Yu Jiang, Zhong-Ping Jiang. at - Automatisierungstechnik, 2012

1,026 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computational Theory and Mathematics, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/efed7c026ed54d75539c013ceb6cc5c08d43a045

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computational Theory and Mathematics

In Electrical and Electronic Engineering

Citations in the corpus

Reinforcement-Learning-Based Robust Controller Design for Continuous-Time Uncertain Nonlinear Systems Subject to Input Constraints (2015, methodology): “By using integral RL algorithms, the system state needs to be reset at each iteration step and it gives rise to difficulties for stability analysis [42].”
Adaptive Dynamic Programming and Adaptive Optimal Output Regulation of Linear Systems (2016, methodology): “This note aims at generalizing the main result of [19] to computational adaptive optimal tracking with disturbance rejection under relaxed assumptions.”
Online adaptive optimal control for continuous-time Markov jump linear systems using a novel policy iteration algorithm (2015, positive): “Thereafter, the approach was then extended to similar systems with completely unknown system dynamics in [7].”
Adaptive Critic Nonlinear Robust Control: A Survey (2017, methodology): “In this sense, the robust ADP method can be regarded as a nonlinear variant of [135], where a computational adaptive optimal control strategy was proposed to iteratively solve the linear algebraic Riccati equation using online information of state and input.”
Adaptive Dynamic Programming for Control: A Survey and Recent Advances (2021, background): “Under the relaxation of some assumptions, the conclusion was further generalized in [160].”
Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness (2019, background): “archers, with problems ranging from PIDlike control [9] to model reference control and output tracking [10], [11], [12], [13], [14], predictive [15], [16], robust [17] and optimal control [18], [19], [20], [21], [22], [23], [24], the latter being one of the most frequently considered problems. The c”
Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning (2014, methodology): “Later, inspired by Vrabie and Lewis (2009) and Vrabie et al. (2009), some online PI algorithms were presented to solve the optimal regulation problem for completely unknown linear systems (Jiang & Jiang, 2012; Lee, Park, & Choi, 2012).”
$ {H}_{ {\infty }}$ Tracking Control of Completely Unknown Continuous-Time Systems via Off-Policy Reinforcement Learning (2015, methodology): “[37], inspired by [21] and [22], proposed an efficient off-policy RL algorithm to learn the solution to the HJI equation.”
Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning (2014, methodology): “For linear systems which are the focus of this technical note, PI has been effectively used to solve the optimal regulator problem for both DT systems [11]–[13] and CT systems [14]–[16].”
Model-Free Optimal Tracking Control via Critic-Only Q-Learning (2016, background): “Note that most of the existing related works [12], [24], [42], [51], [66], [68], [79], [80] belong to the on-policy learning framework or use on-policy implementation.”