Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

2021/06/08 by Michael Poli, Poli, Michael, Stefano Massaroli +16 · 3 citations
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning and Algorithms #Model Reduction and Neural Networks #Neural and Evolutionary Computing (cs.NE) #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #cs.LG #cs.NE #cs.SY #eess.SY #electronic engineering #information engineering #math.DS

paper · pdf · doi:10.48550/arxiv.2106.04165

arxiv created 2021/06/08 · openalex publication_date 2021/06/08 · arxiv updated 2021/06/09 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

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.

Citations

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Neural Spline Flows
• Intensity-Free Learning of Temporal Point Processes
• Dissecting Neural ODEs
• Numerical optimization
• Neural Ordinary Differential Equations for Intervention Modeling

Cited by

• CHyLL: Learning Continuous Neural Representations of Hybrid Systems
• SAC-MoE: Reinforcement Learning with Mixture-of-Experts for Control of Hybrid Dynamical Systems with Uncertainty
• Physics-Embedded Neural ODEs for Sim2Real Edge Digital Twins of Hybrid Power Electronics Systems

Related

• CHyLL: Learning Continuous Neural Representations of Hybrid Systems
• Unsupervised Learning for Nonlinear PieceWise Smooth Hybrid Systems
• Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding
• Neural Jump Stochastic Differential Equations
• Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation