On-Policy Data-Driven Linear Quadratic Regulator via Model Reference Adaptive Reinforcement Learning
- Resource Type
- Conference
- Authors
- Borghesi, Marco; Bosso, Alessandro; Notarstefano, Giuseppe
- Source
- 2023 62nd IEEE Conference on Decision and Control (CDC) Decision and Control (CDC), 2023 62nd IEEE Conference on. :32-37 Dec, 2023
- Subject
- Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Linear systems
Adaptation models
Regulators
Optimal control
Reinforcement learning
Trajectory
Behavioral sciences
- Language
- ISSN
- 2576-2370
In this paper, we address a data-driven linear quadratic optimal control problem in which the regulator design is performed on-policy by resorting to approaches from reinforcement learning and model reference adaptive control. In particular, a continuous-time identifier of the value function is used to generate online a reference model for the adaptive stabilizer. By introducing a suitably selected dithering signal, the resulting policy is shown to achieve asymptotic convergence to the optimal gain while the controlled plant reaches asymptotically the behavior of the optimal closed-loop system.