1 code implementation • 8 May 2024 • Joseph A. Vincent, Haruki Nishimura, Masha Itkina, Paarth Shah, Mac Schwager, Thomas Kollar
To rigorously evaluate behavior cloning policies, we present a framework that provides a tight lower-bound on robot performance in an arbitrary environment, using a minimal number of experimental policy rollouts.
1 code implementation • 15 Oct 2022 • Joseph A. Vincent, Mac Schwager
We then develop algorithms using this tool to compute invariant sets and regions of attraction (ROAs) for control systems with neural networks in the feedback loop.
1 code implementation • 23 Nov 2020 • Joseph A. Vincent, Mac Schwager
We present a method for computing exact reachable sets for deep neural networks with rectified linear unit (ReLU) activation.