2 code implementations • NeurIPS 2021 • Tuomas Oikarinen, Wang Zhang, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng
To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against $l_p$-norm bounded adversarial attacks.
1 code implementation • 16 Dec 2023 • Wang Zhang, Ziwen Ma, Subhro Das, Tsui-Wei Weng, Alexandre Megretski, Luca Daniel, Lam M. Nguyen
Neural networks are powerful tools in various applications, and quantifying their uncertainty is crucial for reliable decision-making.
no code implementations • 23 Jan 2017 • Mark M. Tobenkin, Ian R. Manchester, Alexandre Megretski
Model instability and poor prediction of long-term behavior are common problems when modeling dynamical systems using nonlinear "black-box" techniques.
no code implementations • 16 Jul 2021 • Xinyi Chen, Udaya Ghai, Elad Hazan, Alexandre Megretski
We study online control of an unknown nonlinear dynamical system that is approximated by a time-invariant linear system with model misspecification.
no code implementations • 29 Sep 2021 • Victor Rong, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng
Recent developments on the robustness of neural networks have primarily emphasized the notion of worst-case adversarial robustness in both verification and robust training.
no code implementations • 29 Sep 2021 • Wang Zhang, Lam M. Nguyen, Subhro Das, Pin-Yu Chen, Sijia Liu, Alexandre Megretski, Luca Daniel, Tsui-Wei Weng
In verification-based robust training, existing methods utilize relaxation based methods to bound the worst case performance of neural networks given certain perturbation.
no code implementations • 30 Aug 2022 • Nikolaos Skouloudis, Alexandre Megretski
We design a controller for an agent whose mission is to reach a stationary target while avoiding a family of obstacles which are not known a-priori.
1 code implementation • 11 Feb 2023 • Wang Zhang, Tsui-Wei Weng, Subhro Das, Alexandre Megretski, Luca Daniel, Lam M. Nguyen
Deep neural networks (DNN) have shown great capacity of modeling a dynamical system; nevertheless, they usually do not obey physics constraints such as conservation laws.