Finite-horizon optimal control of discrete-time linear systems with completely unknown dynamics using Q-learning
DOI10.3934/JIMO.2020030zbMATH Open1476.49046OpenAlexW3008992851MaRDI QIDQ1983705FDOQ1983705
Publication date: 10 September 2021
Published in: Journal of Industrial and Management Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.3934/jimo.2020030
Recommendations
- Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
- Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
- Finite-horizon near optimal adaptive control of uncertain linear discrete-time systems
- Finite-time stochastic linear quadratic optimal control based on \(Q\)-learning
- Optimal control for unknown mean-field discrete-time system based on Q-learning
Optimality conditions for problems involving relations other than differential equations (49K21) Linear-quadratic optimal control problems (49N10) Problems with incomplete information (optimization) (49N30) Discrete-time control/observation systems (93C55)
Cites Work
- Title not available (Why is that?)
- Approximate Dynamic Programming
- Data-based approximate policy iteration for affine nonlinear continuous-time optimal control design
- Global Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems
- Output-feedback adaptive optimal control of interconnected systems based on robust adaptive dynamic programming
- Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
- Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
- Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
- Finite-horizon optimal control of discrete-time switched linear systems
- Integral \(Q\)-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems
- A neural network solution for fixed-final time optimal control of nonlinear systems
- Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
- Indefinite LQ optimal control with process state inequality constraints for discrete-time uncertain systems
- Optimal tracking control for networked control systems with random time delays and packet dropouts
- Reinforcement learning for optimal feedback control. A Lyapunov-based approach
- Finite-horizon near optimal adaptive control of uncertain linear discrete-time systems
- Online adaptive optimal control for continuous-time nonlinear systems with completely unknown dynamics
- Optimal stopping investment with non-smooth utility over an infinite time horizon
- A novel optimal tracking control scheme for a class of discrete-time nonlinear systems using generalised policy iteration adaptive dynamic programming algorithm
Cited In (5)
- Data-driven policy iteration algorithm for continuous-time stochastic linear-quadratic optimal control problems
- Data-based \(\mathcal{L}_2\) gain optimal control for discrete-time system with unknown dynamics
- Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning
- Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems
- A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
This page was built for publication: Finite-horizon optimal control of discrete-time linear systems with completely unknown dynamics using Q-learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1983705)
