Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Abstract
Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism for dynamical systems subject to discrete, possibly stochastic, state jumps and multi-modal continuous-time flows. Despite the versatility and importance of SHSs across applications, a general procedure for the explicit learning of both discrete events and multi-mode continuous dynamics remains an open problem. This work introduces Neural Hybrid Automata (NHAs), a recipe for learning SHS dynamics without a priori knowledge on the number of modes and inter-modal transition dynamics. NHAs provide a systematic inference method based on normalizing flows, neural differential equations and self-supervision. We showcase NHAs on several tasks, including mode recovery and flow learning in systems with stochastic transitions, and end-to-end learning of hierarchical robot controllers.
Cite
@article{arxiv.2106.04165,
title = {Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions},
author = {Michael Poli and Stefano Massaroli and Luca Scimeca and Seong Joon Oh and Sanghyuk Chun and Atsushi Yamashita and Hajime Asama and Jinkyoo Park and Animesh Garg},
journal= {arXiv preprint arXiv:2106.04165},
year = {2021}
}