Learning Stable Deep Dynamics Models

Abstract

Deep networks are commonly used to model dynamical systems, predicting how the state of a system will evolve over time (either autonomously or in response to control inputs). Despite the predictive power of these systems, it has been difficult to make formal claims about the basic properties of the learned systems. In this paper, we propose an approach for learning dynamical systems that are guaranteed to be stable over the entire state space. The approach works by jointly learning a dynamics model and Lyapunov function that guarantees non-expansiveness of the dynamics under the learned Lyapunov function. We show that such learning systems are able to model simple dynamical systems and can be combined with additional deep generative models to learn complex dynamics, such as video textures, in a fully end-to-end fashion.

NeurIPS 2019

References in corpus (4)

• Continuous Deep Q-Learning with Model-based Acceleration
• Input Convex Neural Networks
• The Lyapunov Neural Network: Adaptive Stability Certification for Safe Learning of Dynamical Systems
• Optimal Control Via Neural Networks: A Convex Approach

Cited by in corpus (12)

• Physics-informed linear regression is competitive with two Machine Learning methods in residential building MPC
• Active Learning in Robotics: A Review of Control Principles
• Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities
• Neural Lyapunov Differentiable Predictive Control
• Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Prediction
• A Data Driven Method for Computing Quasipotentials
• MMP++: Motion Manifold Primitives with Parametric Curve Models
• Neural Identification for Control
• Learning Safe Neural Network Controllers with Barrier Certificates
• Lyapunov-Regularized Reinforcement Learning for Power System Transient Stability