Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques

DOI10.1080/00207721.2018.1498557zbMath1482.93316OpenAlexW2883304004MaRDI QIDQ5027818

Guang-Hong Yang, Dong Liu

Publication date: 7 February 2022

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207721.2018.1498557

zbMATH Keywords

reinforcement learningdiscrete-time nonlinear systemsdata-driven controlmodel-free adaptive control

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Adaptive control/observation systems (93C40) Discrete-time control/observation systems (93C55)

Related Items (5)

Discrete‐time extended state observer‐based model‐free adaptive sliding mode control with prescribed performance ⋮ Model-free direct adaptive controller based on quantum-inspired fuzzy rules network for a class of unknown discrete-time systems ⋮ Learning output reference model tracking for higher-order nonlinear systems with unknown dynamics ⋮ Enhanced model-free adaptive iterative learning control with load disturbance and data dropout ⋮ Prescribed performance controller with affine equivalent model for a class of unknown nonlinear discrete-time systems

Cites Work

• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Barrier Lyapunov functions for Nussbaum gain adaptive control of full state constrained nonlinear systems
• Data-driven approximate value iteration with optimality error bound analysis
• Adaptive control-based barrier Lyapunov functions for a class of stochastic nonlinear systems with full state constraints
• Adaptive dynamic programming for control. Algorithms and stability
• From experiment design to closed-loop control
• Data-driven control of nonlinear systems: an on-line direct approach
• Extensions to ``Virtual reference feedback tuning: A direct method for the design of feedback controllers
• A survey on iterative learning control for nonlinear systems
• Virtual reference direct design method: an off-line approach to data-based control system design
• New results on the synthesis of PID controllers
• Distributed Reinforcement Learning via Gossip
• Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning
• Data-driven criteria synthesis of system with two-degree-of-freedom controller

This page was built for publication: Model-free adaptive control design for nonlinear discrete-time processes with reinforcement learning techniques