A Q-learning predictive control scheme with guaranteed stability

DOI10.1016/j.ejcon.2020.03.001zbMath1455.93049OpenAlexW3010920281MaRDI QIDQ2220029

Stefan Streif, Pavel Osinenko, Lukas Beckenbach

Publication date: 21 January 2021

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

Full work available at URL: https://doi.org/10.1016/j.ejcon.2020.03.001

zbMATH Keywords

predictive controlQ-learningnominal stabilitycost shaping

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Discrete-time control/observation systems (93C55) Asymptotic stability in control theory (93D20) Model predictive control (93B45)

Related Items (1)

Experimental study on a novel simultaneous control and identification of a 3-DOF delta robot using model reference adaptive control

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Provably safe and robust learning-based model predictive control
• Adaptive dynamic programming for control. Algorithms and stability
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Complete stability analysis of a heuristic approximate dynamic programming control design
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• A quasi-infinite horizon nonlinear model predictive control scheme with guaranteed stability
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Feasibility and stability of constrained finite receding horizon control
• \({\mathcal Q}\)-learning
• Nonlinear model-based control using second-order Volterra models
• Constrained model predictive control: Stability and optimality
• Nonlinear model predictive control. Theory and algorithms
• Unconstrained model predictive control and suboptimality estimates for nonlinear continuous-time systems
• Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
• Stabilization of nonlinear systems with state and control constraints using Lyapunov-based predictive control
• Approximate dynamic programming-based approaches for input--output data-driven control of nonlinear processes
• Dynamic programming and suboptimal control: a survey from ADP to MPC
• Analysis and Design of Unconstrained Nonlinear MPC Schemes for Finite and Infinite Dimensional Systems
• An analysis of temporal-difference learning with function approximation
• Contractive model predictive control for constrained nonlinear systems
• Unconstrained receding-horizon control of nonlinear systems
• Lyapunov-Based Model Predictive Control of Nonlinear Systems Subject to Data Losses
• On the Infinite Horizon Performance of Receding Horizon Controllers
• Data-Driven Economic NMPC Using Reinforcement Learning
• Performance Guarantees for Model-Based Approximate Dynamic Programming in Continuous Spaces
• Model predictive control: for want of a local control Lyapunov function, all is not lost
• On the stability of constrained MPC without terminal constraint

This page was built for publication: A Q-learning predictive control scheme with guaranteed stability