Enforcing robust control guarantees within neural network policies
From MaRDI portal
Publication:6353860
arXiv2011.08105MaRDI QIDQ6353860
J. Zico Kolter, Mahyar Fazlyab, Melrose Roderick, Priya L. Donti
Publication date: 16 November 2020
Abstract: When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rigorous guarantees on system stability under certain worst-case disturbances, they often yield simple controllers that perform poorly in the average (non-worst) case. In contrast, nonlinear control methods trained using deep learning have achieved state-of-the-art performance on many control tasks, but often lack robustness guarantees. In this paper, we propose a technique that combines the strengths of these two approaches: constructing a generic nonlinear control policy class, parameterized by neural networks, that nonetheless enforces the same provable robustness criteria as robust control. Specifically, our approach entails integrating custom convex-optimization-based projection layers into a neural network-based policy. We demonstrate the power of this approach on several domains, improving in average-case performance over existing robust control methods and in worst-case stability over (non-robust) deep RL methods.
Has companion code repository: https://github.com/locuslab/robust-nn-control
This page was built for publication: Enforcing robust control guarantees within neural network policies
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353860)
