Modified value-function-approximation for synchronous policy iteration with single-critic configuration for nonlinear optimal control

DOI10.1080/00207179.2019.1648874zbMath1475.49031OpenAlexW2965185729MaRDI QIDQ5157945

Lei Chen, Eric Hu, Zhao Feng Tian, Difan Tang

Publication date: 20 October 2021

Published in: International Journal of Control (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/2440/124816

zbMATH Keywords

optimal controlnonlinear controlneural networkspolicy iterationapproximate dynamic programmingadaptive dynamic programming

Mathematics Subject Classification ID

Dynamic programming in optimal control and differential games (49L20) Dynamic programming (90C39) Discrete approximations in optimal control (49M25)

Related Items (3)

Learning feedback Nash strategies for nonlinear port-Hamiltonian systems ⋮ Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems ⋮ SOS-based policy iteration for H_∞ control of polynomial systems with uncertain parameters

Cites Work

• Unnamed Item
• Unnamed Item
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Robust adaptive dynamic programming for linear and nonlinear systems: an overview
• Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning
• Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
• Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• The method of weighted residuals and variational principles. With application in fluid mechanics, heat and mass transfer
• Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation
• Reinforcement learning solution for HJB equation arising in constrained optimal control problem
• Multilayer feedforward networks are universal approximators
• A novel actor-critic-identifier architecture for approximate optimal control of uncertain nonlinear systems
• Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Novel iterative neural dynamic programming for data-based approximate optimal control design
• Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach
• Online adaptive optimal control for continuous-time nonlinear systems with completely unknown dynamics
• Neural-network-observer-based optimal control for unknown nonlinear systems using adaptive dynamic programming
• Online adaptive algorithm for optimal control with integral reinforcement learning
• An adaptive critic-based scheme for consensus control of nonlinear multi-agent systems
• Global Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems
• An Approximation Theory of Optimal Control for Trainable Manipulators
• Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints
• Real-time neural inverse optimal control for a linear induction motor
• Online solution of nonlinear two‐player zero‐sum games using synchronous policy iteration
• Online H∞ control for completely unknown nonlinear systems via an identifier–critic-based ADP structure

This page was built for publication: Modified value-function-approximation for synchronous policy iteration with single-critic configuration for nonlinear optimal control