Switching Linear Dynamics for Variational Bayes Filtering

Abstract

System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning. Despite their complexity, such systems can often be approximated well by a set of linear dynamical systems if broken into appropriate subsequences. This mechanism not only helps us find good approximations of dynamics, but also gives us deeper insight into the underlying system. Leveraging Bayesian inference, Variational Autoencoders and Concrete relaxations, we show how to learn a richer and more meaningful state space, e.g. encoding joint constraints and collisions with walls in a maze, from partial and high-dimensional observations. This representation translates into a gain of accuracy of learned dynamics showcased on various simulated tasks.

Appears in Proceedings of the 36th International Conference on Machine Learning (ICML)

Cited by in corpus (12)

• Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning
• Learning to Fly via Deep Model-Based Reinforcement Learning
• Structured Object-Aware Physics Prediction for Video Modeling and Planning
• On learning latent dynamics of the AUG plasma state
• Deep Explicit Duration Switching Models for Time Series
• Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
• Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning
• Variational Dynamic Mixtures
• Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
• Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
• Deep Switching State Space Model (DS${}^3$M) for Nonlinear Time Series Forecasting with Regime Switching
• Switching Recurrent Kalman Networks