Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training

no code implementations • 21 Nov 2022 • Jiaxu Tian, Dapeng Zhi, Si Liu, Peixin Wang, Guy Katz, Min Zhang

The experimental results on a wide range of benchmarks show that the DNNs trained by using our approach exhibit comparable performance, while the reachability analysis of the corresponding systems becomes more amenable with significant tightness and efficiency improvement over the state-of-the-art white-box approaches.

Decision Making Reinforcement Learning (RL)