Approximate Robust Control of Uncertain Dynamical Systems


This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a principled approach to safety that aims to maximize the worst-case performance of a system. However, the resulting optimization problem is generally intractable for non-linear systems with continuous states. To overcome this issue, we introduce two tractable methods that are based either on sampling or on a conservative approximation of the robust objective. The proposed approaches are applied to the problem of autonomous driving.

32nd Conference on Neural Information Processing Systems (NeurIPS 2018) MLITS Workshop
Edouard Leurent
PhD Student in Reinforcement Learning