ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
Julen Urain,Michele Ginesi,Davide Tateo,Jan Peters,Julen Urain,Michele Ginesi,Davide Tateo,Jan Peters
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations. We prove the Lyapunov stability for a class of Stochastic Differential Equations and we propose a learning algorithm to learn them from a set of demonstrated tr...
