An approach to solving optimal control problems of nonlinear systems by introducing detail-reward mechanism in deep reinforcement learning

DOI10.3934/mbe.2022430OpenAlexW4285214290MaRDI QIDQ2688600

Ze Cui, Xiaochen Liu, Shixuan Yao, Ying-Hui Zhang

Publication date: 3 March 2023

Published in: Mathematical Biosciences and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/mbe.2022430

zbMATH Keywords

Lyapunov functionreinforcement learningdetail-reward mechanism (DRM)Hamilton-Jacobi-Bellman (HJB)nonlinear control system (NCS)

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Existence theories for optimal control problems involving partial differential equations (49J20) Hamilton-Jacobi equations (35F21)

Cites Work

• Unnamed Item
• Unnamed Item
• An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games
• Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
• Limit-cycle-like control for 2-dimensional discrete-time nonlinear control systems and its application to the Hénon map
• Stability analysis of switched systems using variational principles: An introduction
• Approximately bisimilar symbolic models for nonlinear control systems
• Approximate solutions to the time-invariant Hamilton-Jacobi-Bellman equation
• Fuzzy model-based predictive control using Takagi-Sugeno models
• Stabilization of Lur'e-type nonlinear control systems by Lyapunov-Krasovskii functionals
• \({\mathcal Q}\)-learning
• An iterative \(\varepsilon\)-optimal control scheme for a class of discrete-time nonlinear systems with unfixed initial state
• Optimal control and applications to aerospace: some results and challenges
• Self-learning robust optimal control for continuous-time nonlinear systems with mismatched disturbances
• Approximate neural optimal control with reinforcement learning for a torsional pendulum device
• Open-loop optimal controller design using variational iteration method
• Discrete-Time Terminal Sliding Mode Control Systems Based on Euler's Discretization
• An Optimal Control Scheme for a Class of Discrete-time Nonlinear Systems with Time Delays Using Adaptive Dynamic Programming
• The Relationship between the Maximum Principle and Dynamic Programming
• The Euclidean Space Controllability of Control Systems with Delay
• Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning
• Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints
• An Overview of Research on Adaptive Dynamic Programming
• Adaptive quantized control for uncertain nonlinear systems with unknown control directions