Online accelerated data-driven learning for optimal feedback control of discrete-time partially uncertain systems

DOI10.1002/ACS.3729zbMATH Open1545.49021MaRDI QIDQ6558271FDOQ6558271

Authors: Luke Somers, Wassim M. Haddad, Nick-Marios T. Kokolakis, Kyriakos G. Vamvoudakis 

Publication date: 19 June 2024

Published in: International Journal of Adaptive Control and Signal Processing (Search for Journal in Brave)

Recommendations

• Output‐feedback robust control of systems with uncertain dynamics via data‐driven policy learning
• Online adaptive algorithm for with integral reinforcement learning
• Online identifier-actor-critic algorithm for optimal control of nonlinear systems
• Learning‐based T‐sHDP() for optimal control of a class of nonlinear discrete‐time systems
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem

zbMATH Keywords

discrete-time systemsoptimal controlonline learningapproximate dynamic programminguniform ultimate boundednesshigh-order tunersmomentum-based learning

Mathematics Subject Classification ID

Optimality conditions for problems involving relations other than differential equations (49K21) Dynamic programming in optimal control and differential games (49L20) Feedback control (93B52) Discrete-time control/observation systems (93C55)

Cites Work

• Introductory lectures on convex optimization. A basic course.
• Nonlinear dynamical systems and control. A Lyapunov-based approach
• Approximate Dynamic Programming
• Neural network control of nonlinear discrete-time systems.
• Reinforcement learning. An introduction
• Adaptive dynamic programming with applications in optimal control
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
• Robust adaptive dynamic programming
• Title not available (Why is that?)
• Nonquadratic cost and nonlinear feedback control
• Numerical solutions to the Bellman equation of optimal control
• A variational perspective on accelerated methods in optimization
• Reinforcement learning for optimal feedback control. A Lyapunov-based approach
• An algorithm to solve the discrete HJI equation arising in the L2 gain optimization problem
• Optimal Distributed Convex Optimization on Slowly Time-Varying Graphs
• Matrix theory and applications for scientists and engineers

Cited In (1)

• Learning‐based T‐sHDP() for optimal control of a class of nonlinear discrete‐time systems

This page was built for publication: Online accelerated data-driven learning for optimal feedback control of discrete-time partially uncertain systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6558271)