Reinforcement-learning-based online learning control for discrete-time unknown nonaffine nonlinear systems

DOI10.1142/9789814616881_0002MaRDI QIDQ3467686zbMATH OpenOpenAlexFDO

Authors Xiong Yang, Derong Liu, Qinglai Wei, Ding Wang

Publication date 4 February 2016

Published in Frontiers of Intelligent Control and Information Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/9789814616881_0002

zbMATH Keywords

heuristic dynamic programmingLyapunov's direct methodneural networks (NNs)discrete-time unknown nonaffine nonlinear systemsonline learning control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Dynamic programming (90C39) Neural networks for/in biological studies, artificial life and related topics (92B20) Nonlinear systems in control theory (93C10) Multivariable systems, multidimensional control systems (93C35) Discrete-time control/observation systems (93C55) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05)

Recommendations

• Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning
• Direct adaptive control for a class of discrete‐time unknown nonaffine nonlinear systems using neural networks
• Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints
• Multigradient recursive reinforcement learning nn control for affine nonlinear systems with unmodeled dynamics
• Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques

Cited in

(6)

• Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques
• RL-based adaptive control for a class of non-affine uncertain stochastic systems with mismatched disturbances
• On-the-Fly Control of Unknown Nonlinear Systems With Sublinear Regret
• Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning
• Multigradient recursive reinforcement learning nn control for affine nonlinear systems with unmodeled dynamics
• Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems

This page was built for publication: Reinforcement-learning-based online learning control for discrete-time unknown nonaffine nonlinear systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3467686)