1 code implementation • 31 Mar 2023 • YiXuan Wang, Weichao Zhou, Jiameng Fan, Zhilu Wang, Jiajun Li, Xin Chen, Chao Huang, Wenchao Li, Qi Zhu
We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions.
2 code implementations • 25 Jun 2021 • Chao Huang, Jiameng Fan, Zhilu Wang, YiXuan Wang, Weichao Zhou, Jiajun Li, Xin Chen, Wenchao Li, Qi Zhu
We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs).
1 code implementation • 26 Feb 2021 • Jiameng Fan, Wenchao Li
This approach enables us to train high-performance policies that are robust to visual distractions and can generalize well to unseen environments.
1 code implementation • 13 Aug 2020 • Jiameng Fan, Wenchao Li
We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks.
1 code implementation • 25 Jun 2019 • Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen, Qi Zhu
In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i. e., as long as they ensure that the neural networks are Lipschitz continuous.
no code implementations • 6 Mar 2019 • Jiameng Fan, Wenchao Li
An important facet of reinforcement learning (RL) has to do with how the agent goes about exploring the environment.