Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator
Abstract
Risk-aware control, though with promise to tackle unexpected events, requires a known exact dynamical model. In this work, we propose a model-free framework to learn a risk-aware controller with a focus on the linear system. We formulate it as a discrete-time infinite-horizon LQR problem with a state predictive variance constraint. To solve it, we parameterize the policy with a feedback gain pair and leverage primal-dual methods to optimize it by solely using data. We first study the optimization landscape of the Lagrangian function and establish the strong duality in spite of its non-convex nature. Alongside, we find that the Lagrangian function enjoys an important local gradient dominance property, which is then exploited to develop a convergent random search algorithm to learn the dual function. Furthermore, we propose a primal-dual algorithm with global convergence to learn the optimal policy-multiplier pair. Finally, we validate our results via simulations.
Cite
@article{arxiv.2011.10931,
title = {Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator},
author = {Feiran Zhao and Keyou You},
journal= {arXiv preprint arXiv:2011.10931},
year = {2021}
}
Comments
To appear in the Annual Conference on Learning for Dynamics and Control (L4DC) 2021