Learning for MPC with stability \& safety guarantees
From MaRDI portal
Publication:2097756
Abstract: The combination of learning methods with Model Predictive Control (MPC) has attracted a significant amount of attention in the recent literature. The hope of this combination is to reduce the reliance of MPC schemes on accurate models, and to tap into the fast developing machine learning and reinforcement learning tools to exploit the growing amount of data available for many systems. In particular, the combination of reinforcement learning and MPC has been proposed as a viable and theoretically justified approach to introduce explainable, safe and stable policies in reinforcement learning. However, a formal theory detailing how the safety and stability of an MPC-based policy can be maintained through the parameter updates delivered by the learning tools is still lacking. This paper addresses this gap. The theory is developed for the generic Robust MPC case, and applied in simulation in the robust tube-based linear MPC case, where the theory is fairly easy to deploy in practice. The paper focuses on Reinforcement Learning as a learning tool, but it applies to any learning method that updates the MPC parameters online.
Recommendations
- Provably safe and robust learning-based model predictive control
- Online learning with stability guarantees: a memory-based warm starting for real-time MPC
- A Q-learning predictive control scheme with guaranteed stability
- Stability-constrained Markov decision processes using MPC
- ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions
Cites work
- A model for system uncertainty in reinforcement learning
- Data-Driven Economic NMPC Using Reinforcement Learning
- Guaranteed Closed-Loop Learning in Model Predictive Control
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Input-to-state stability for discrete-time nonlinear systems
- Introduction to sensitivity and stability analysis in nonlinear programming
- MPC for tracking piecewise constant references for constrained linear systems
- Provably safe and robust learning-based model predictive control
- Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
- Robust model predictive control of constrained linear systems with bounded disturbances
- Robust MPC via min-max differential inequalities
- Safe Reinforcement Learning Using Robust MPC
- Systems with persistent disturbances: Predictive control with restricted constraints
- Tube-based robust nonlinear model predictive control
Cited in
(13)- Stability-constrained Markov decision processes using MPC
- Online learning with stability guarantees: a memory-based warm starting for real-time MPC
- A Q-learning predictive control scheme with guaranteed stability
- ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions
- Stability of controllers for Gaussian process dynamics
- Provably safe and robust learning-based model predictive control
- Learning-based state estimation and control using MHE and MPC schemes with imperfect models
- Safe learning-based model predictive control using the compatible models approach
- Safe control of nonlinear systems in LPV framework using model-based reinforcement learning
- Stabilizing reinforcement learning control: a modular framework for optimizing over all stable behavior
- Multi-agent reinforcement learning via distributed MPC as a function approximator
- Input-to-state stabilizing extreme learning machine-based model predictive control under denial-of-service attack
- Model predictive control: past, present, and future
This page was built for publication: Learning for MPC with stability \& safety guarantees
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2097756)
