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.

References in corpus (9)

• Scikit-learn: Machine Learning in Python
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Dissecting Neural ODEs
• Neural Spline Flows
• Learning Neural Event Functions for Ordinary Differential Equations
• Intensity-Free Learning of Temporal Point Processes
• Neural Ordinary Differential Equations for Intervention Modeling
• Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models
• Neural Spatio-Temporal Point Processes