Online identifier–actor–critic algorithm for optimal control of nonlinear systems

DOI10.1002/oca.2259zbMath1370.49021OpenAlexW2343875079MaRDI QIDQ5280130

Derong Liu, Qinglai Wei, Hanquan Lin

Publication date: 20 July 2017

Published in: Optimal Control Applications and Methods (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/oca.2259

zbMATH Keywords

optimal controlneural networknonlinear systemonline learningLyapunov methoddiscrete-timeadaptive dynamic programming

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) Discrete-time control/observation systems (93C55) Dynamic programming (90C39)

Related Items (5)

Global dynamics of a fractional order model for the transmission of HIV epidemic with optimal control ⋮ Adaptive critic optimization to decentralized event‐triggered control of continuous‐time nonlinear interconnected systems ⋮ A New Integral Critic Learning for Optimal Tracking Control with Applications to Boiler‐Turbine Systems ⋮ Sliding-mode surface-based approximate optimal control for nonlinear multiplayer Stackelberg-Nash games via adaptive dynamic programming ⋮ Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning

Cites Work

• Unnamed Item
• Optimal control of unknown affine nonlinear discrete-time systems using offline-trained neural networks with proof of convergence
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming
• Integral \(Q\)-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms.
• A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Approximate dynamic programming-based approaches for input--output data-driven control of nonlinear processes
• Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach
• On integral generalized policy iteration for continuous-time linear quadratic regulations

This page was built for publication: Online identifier–actor–critic algorithm for optimal control of nonlinear systems