Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems

DOI10.1016/j.automatica.2020.109035zbMath1447.93177OpenAlexW3027032642MaRDI QIDQ2188278

Bo Pang, Zhong-Ping Jiang, Mareels, Iven M. Y.

Publication date: 10 June 2020

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2020.109035

zbMATH Keywords

optimal controlreinforcement learning (RL)adaptive dynamic programming (ADP)policy iteration (PI)

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Linear systems in control theory (93C05) Existence theories for optimal control problems involving ordinary differential equations (49J15)

Related Items

Human motor learning is robust to control-dependent noise, An improved iterative algorithm for solving optimal tracking control problems of stochastic systems, A Lyapunov characterization of robust policy optimization, Suboptimal reduced control of unknown nonlinear singularly perturbed systems via reinforcement learning, Adaptive optimal control of affine nonlinear systems via identifier-critic neural network approximation with relaxed PE conditions, Optimal output tracking control of linear discrete-time systems with unknown dynamics by adaptive dynamic programming and output feedback, Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method, Incremental reinforcement learning and optimal output regulation under unmeasurable disturbances, Optimal control for unknown mean-field discrete-time system based on Q-Learning

Uses Software

• Visual MISER

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Efficient model-based reinforcement learning for approximate online optimal control
• Adaptive dynamic programming and optimal control of nonlinear nonaffine systems
• A unified Floquet theory for discrete, continuous, and hybrid periodic linear systems
• An exact penalty function method for continuous inequality constrained optimal control problem
• Visual MISER: an efficient user-friendly visual program for solving optimal control problems
• The Riccati equation
• Gradient-based approach to solve optimal periodic output feedback control problems
• Reinforcement learning for optimal feedback control. A Lyapunov-based approach
• Dual-loop iterative optimal control for the finite horizon LQR problem with unknown dynamics
• Adaptive systems: an introduction
• \(\mathcal H_2\) norm of linear time-periodic systems: a perturbation analysis
• On solving periodic Riccati equations
• On the Phase Portrait of the Matrix Riccati Equation Arising from the Periodic Control Problem
• An Approximation Theory of Optimal Control for Trainable Manipulators
• Adaptive Robust Output Regulation of Uncertain Linear Periodic Systems
• Robust Adaptive Dynamic Programming
• Adaptive identification and control of linear periodic systems using second‐level adaptation
• Stability analysis of continuous-time periodic systems via the harmonic analysis
• A New Periodic Adaptive Control Approach for Time-Varying Parameters With Known Periodicity
• A first course in harmonic analysis