Data-driven nonlinear near-optimal regulation based on iterative neural dynamic programming

DOI10.16383/J.AAS.2017.C160272MaRDI QIDQ3130924zbMATH OpenOpenAlexWikidataFDO

Authors Ding Wang, Chaoxu Mu, Derong Liu

Publication date 29 January 2018

Full work available at URL https://doi.org/10.16383/j.aas.2017.c160272

zbMATH Keywords

adaptive dynamic programmingdata-driven controliterative neural dynamic programmingneural networksnonlinear near-optimal regulation

Mathematics Subject Classification ID

Dynamic programming (90C39) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) Adaptive control/observation systems (93C40) Discrete-time control/observation systems (93C55)

Recommendations

• Novel iterative neural dynamic programming for data-based approximate optimal control design
• An iterative adaptive dynamic programming algorithm for optimal control of unknown discrete-time nonlinear systems with constrained inputs
• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• A novel optimal tracking control scheme for a class of discrete-time nonlinear systems using generalised policy iteration adaptive dynamic programming algorithm
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming

Cited in

(10)

• Decentralized adaptive optimal stabilization of nonlinear systems with matched interconnections
• Optimal control of complex systems based on improved dual heuristic dynamic programming algorithm
• Neural network robust tracking control with adaptive critic framework for uncertain nonlinear systems
• Novel iterative neural dynamic programming for data-based approximate optimal control design
• Discrete non-linear adaptive data driven control based upon simultaneous perturbation stochastic approximation
• Connectivity preservation of second-order nonlinear multiagent systems with hybrid event-driven and time-driven control
• Online H∞ control for completely unknown nonlinear systems via an identifier–critic-based ADP structure
• Neural-network-based discounted optimal control via an integrated value iteration with accuracy guarantee
• Single-network ADP for near optimal control of continuous-time zero-sum games without using initial stabilising control laws
• Safety-critical optimal control of discrete-time non-linear systems via policy iteration-based Q-learning

This page was built for publication: Data-driven nonlinear near-optimal regulation based on iterative neural dynamic programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3130924)