Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning

1 code implementation • 23 Dec 2021 • Kai-Chieh Hsu, Vicenç Rubies-Royo, Claire J. Tomlin, Jaime F. Fisac

Recent successes in reinforcement learning methods to approximately solve optimal control problems with performance objectives make their application to certification problems attractive; however, the Lagrange-type objective used in reinforcement learning is not suitable to encode temporal logic requirements.

Q-Learning reinforcement-learning +1