2018-10-23-richards18a.md

title	abstract	keywords	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems	Learning algorithms have shown considerable prowess in simulation by allowing robots to adapt to uncertain environments and improve their performance. However, such algorithms are rarely used in practice on safety-critical systems, since the learned policy typically does not yield any safety guarantees. That is, the required exploration may cause physical harm to the robot or its environment. In this paper, we present a method to learn accurate safety certificates for nonlinear, closed-loop dynamical systems. Specifically, we construct a neural network Lyapunov function and a training algorithm that adapts it to the shape of the largest safe region in the state space. The algorithm relies only on knowledge of inputs and outputs of the dynamics, rather than on any specific model structure. We demonstrate our method by learning the safe region of attraction for a simulated inverted pendulum. Furthermore, we discuss how our method can be used in safe learning algorithms together with statistical models of dynamical systems.	Lyapunov stability, Safe learning, Reinforcement learning	inproceedings	Proceedings of Machine Learning Research	richards18a	0	The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems	466	476	466-476	466	false	Richards, Spencer M. and Berkenkamp, Felix and Krause, Andreas	given family Spencer M. Richards given family Felix Berkenkamp given family Andreas Krause	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/richards18a/richards18a.pdf	label link Source code https://github.com/befelix/safe_learning