Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes

1 code implementation • 7 Feb 2024 • Will Lavanakul, Jason J. Choi, Koushil Sreenath, Claire J. Tomlin

As such, we believe that the new notion of the discriminating hyperplane offers a more generalizable direction towards designing safety filters, encompassing and extending existing certificate-function-based or safe RL methodologies.

Reinforcement Learning (RL)