-
Verifiably Safe Exploration for End-to-End Reinforcement Learning
Deploying deep reinforcement learning in safety-critical settings requir...
07/02/2020 ∙ by Nathan Hunt, et al. ∙
22
∙
share
read it
-
Formal Verification of End-to-End Learning in Cyber-Physical Systems: Progress and Challenges
Autonomous systems – such as self-driving cars, autonomous drones, and a...
06/15/2020 ∙ by Nathan Fulton, et al. ∙
0
∙
share
read it
-
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics wh...
07/26/2019 ∙ by Pu Zhao, et al. ∙
6
∙
share
read it
