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 (5)

• Structured Object-Aware Physics Prediction for Video Modeling and Planning
• Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems
• Deep Explicit Duration Switching Models for Time Series
• Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
• Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models