Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning

no code implementations • 11 Apr 2020 • Michael Everett, Bjorn Lutjens, Jonathan P. How

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness.

Adversarial Robustness Collision Avoidance +2