A hybrid dynamical systems perspective on reinforcement learning for cyber-physical systems: vistas, open problems, and challenges

DOI10.1007/978-3-030-60990-0_24zbMath1500.93044OpenAlexW3174756060MaRDI QIDQ2094057

Publication date: 28 October 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-60990-0_24

Learning and adaptive systems in artificial intelligence (68T05) Control/observation systems involving computers (process control, etc.) (93C83) Sampled-data control/observation systems (93C57) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30) Networked control (93B70)

Cites Work

Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
Efficient model-based reinforcement learning for approximate online optimal control
Security concepts for the dynamics of autonomous vehicle networks
Stability analysis for stochastic hybrid systems: a survey
Multivariable adaptive control: a survey
A framework for a class of hybrid extremum seeking controllers with dynamic inclusions
Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
Model-free event-triggered control algorithm for continuous-time linear systems with optimal performance
Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
Reinforcement learning for optimal feedback control. A Lyapunov-based approach
Hybrid mechanisms for robust synchronization and coordination of multi-agent networked sampled-data systems
Optimal sampled-data control systems
Non-equilibrium dynamic games and cyber-physical security: a cognitive hierarchy approach
Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning
Multi-agent discrete-time graphical games and reinforcement learning solutions
From model-based control to data-driven control: survey, classification and perspective
Unified frameworks for sampled-data extremum seeking control: global optimisation and multi-unit systems
Iterative learning control. An optimization paradigm
Robust hybrid zero-order optimization algorithms with acceleration via averaging in time
Lyapunov-Based Sufficient Conditions for Stability of Hybrid Systems With Memory
A Framework for the Event-Triggered Stabilization of Nonlinear Systems
Safe schedulability of bounded-rate multi-mode systems
A Lyapunov Redesign of Coordination Algorithms for Cyber-Physical Systems
Hybrid Control Systems and Viscosity Solutions
Controllability of Nonlinear Discrete-Time Systems: A Lie-Algebraic Approach
Averaging analysis for discrete time and sampled data adaptive systems
Robust adaptive LQ control schemes
An Approximation Theory of Optimal Control for Trainable Manipulators
Numerical Optimization
A unified framework for hybrid control: model and optimal control theory
Optimal control of a class of hybrid systems
A sampled-data iterative learning control using fuzzy network design
A Robust Event-Triggered Approach for Fast Sampled-Data Extremization and Learning
Explicit Computation of the Sampling Period in Emulation of Controllers for Nonlinear Sampled-Data Systems
Unbounded viscosity solutions of hybrid control systems
Primal-Dual Q-Learning Framework for LQR Design
Reinforcement Learning-Based Adaptive Optimal Exponential Tracking Control of Linear Systems With Unknown Dynamics
Hybrid online learning control in networked multiagent systems: A survey
Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles
Convex dynamic programming for hybrid systems
A Framework for Stabilization of Nonlinear Sampled-Data Systems Based on Their Approximate Discrete-Time Models
Logic-Based Solution Methods for Optimal Control of Hybrid Systems
On the Hybrid Optimal Control Problem: Theory and Algorithms
Event-Triggered Real-Time Scheduling of Stabilizing Control Tasks
Hybrid Feedback Control and Robust Stabilization of Nonlinear Systems
Control Perspectives on Numerical Algorithms and Matrix Problems
Uniting Local and Global Output Feedback Controllers
Stability and Performance of SISO Control Systems With First-Order Reset Elements
Extremum-Seeking in Singularly Perturbed Hybrid Systems
Quaternion-Based Hybrid Feedback for Robust Global Attitude Synchronization
Periodic Event-Triggered Control for Linear Systems
Optimal Control for Hybrid Systems With Partitioned State Space
Robust Nonlinear Regulation: Continuous-Time Internal Models and Hybrid Identifiers
Application of predictive control strategies to the management of complex networks in the urban water cycle [Applications of Control]
Online solution of nonlinear two‐player zero‐sum games using synchronous policy iteration
Sufficient conditions for stabilization of sampled-data nonlinear systems via discrete-time approximations
On the equivalence between global recurrence and the existence of a smooth Lyapunov function for hybrid systems
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item

This page was built for publication: A hybrid dynamical systems perspective on reinforcement learning for cyber-physical systems: vistas, open problems, and challenges