no code implementations • 16 Mar 2023 • Taosha Guo, Abed AlRahman Al Makdah, Vishaal Krishnan, Fabio Pasqualetti
In this paper we study an imitation and transfer learning setting for Linear Quadratic Gaussian (LQG) control, where (i) the system dynamics, noise statistics and cost function are unknown and expert data is provided (that is, sequences of optimal inputs and outputs) to learn the LQG controller, and (ii) multiple control tasks are performed for the same system but with different LQG costs.
no code implementations • 1 Apr 2022 • Abed AlRahman Al Makdah, Vishaal Krishnan, Vaibhav Katewa, Fabio Pasqualetti
In this work, we revisit the Linear Quadratic Gaussian (LQG) optimal control problem from a behavioral perspective.
no code implementations • 30 Mar 2021 • Abed AlRahman Al Makdah, Vishaal Krishnan, Fabio Pasqualetti
In this work, we propose a framework to learn feedback control policies with guarantees on closed-loop generalization and adversarial robustness.
no code implementations • NeurIPS 2020 • Vishaal Krishnan, Abed AlRahman Al Makdah, Fabio Pasqualetti
In contrast to regularization-based approaches, we formulate the adversarially robust learning problem as one of loss minimization with a Lipschitz constraint, and show that the saddle point of the associated Lagrangian is characterized by a Poisson equation with weighted Laplace operator.