Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning
From MaRDI portal
Publication:5347323
DOI10.1080/00207721.2016.1236423zbMath1362.93062OpenAlexW2525486061MaRDI QIDQ5347323
Mircea-Bogdan Rădac, Raul-Cristian Roman, Radu-Emil Precup
Publication date: 23 May 2017
Published in: International Journal of Systems Science (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/00207721.2016.1236423
position controldata-driven controlmodel-free controlreinforcement Q-learningvirtual reference feedback tuningaerodynamic system
Learning and adaptive systems in artificial intelligence (68T05) Feedback control (93B52) Nonlinear systems in control theory (93C10) Application models in control theory (93C95) Discrete-time control/observation systems (93C55)
Related Items
Data-driven sliding mode control: a new approach based on optimization, Learning output reference model tracking for higher-order nonlinear systems with unknown dynamics, Adaptive T-S fuzzy controller using reinforcement learning based on Lyapunov stability, Data-driven adaptive dynamic programming for partially observable nonzero-sum games via Q-learning method, Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques, Prescribed performance controller with affine equivalent model for a class of unknown nonlinear discrete-time systems
Cites Work
- Virtual reference feedback tuning for non-minimum phase plants
- Data-driven controller design. The \(H_2\) approach.
- Virtual reference feedback tuning: A direct method for the design of feedback controllers
- \({\mathcal Q}\)-learning
- An overview of population-based algorithms for multi-objective optimisation
- Convergence of the standard RLS method andUDUTfactorisation of covariance matrix for solving the algebraic Riccati equation of the DLQR via heuristic approximate dynamic programming
- Adaptive iterative learning control for a class of non-linearly parameterised systems with input saturations
- Nearly data-based optimal control for linear discrete model-free systems with delays via reinforcement learning
- Robust convergence of the steepest descent method for data-based control
- Data-driven model reference control with asymptotically guaranteed stability
- Model-free control of nonlinear stochastic systems with discrete-time measurements
- Iterative feedback tuning—an overview
- Finite horizon optimal control of non-linear discrete-time switched systems using adaptive dynamic programming with ε-error bound
- Model-free control
- Direct Nonlinear Control Design: The Virtual Reference Feedback Tuning (VRFT) Approach
- Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
- Data-driven criteria synthesis of system with two-degree-of-freedom controller
- Data-based controllability analysis of discrete-time linear time-delay systems