Hybrid system identification using switching density networks

by   Michael Burke, et al.

Behaviour cloning is a commonly used strategy for imitation learning and can be extremely effective in constrained domains. However, in cases where the dynamics of an environment may be state dependent and varying, behaviour cloning places a burden on model capacity and the number of demonstrations required. This paper introduces switching density networks, which rely on a categorical reparametrisation for hybrid system identification. This results in a network comprising a classification layer that is followed by a regression layer. We use switching density networks to predict the parameters of hybrid control laws, which are toggled by a switching layer to produce different controller outputs, when conditioned on an input state. This work shows how switching density networks can be used for hybrid system identification in a variety of tasks, successfully identifying the key joint angle goals that make up manipulation tasks, while simultaneously learning image-based goal classifiers and regression networks that predict joint angles from images. We also show that they can cluster the phase space of an inverted pendulum, identifying the balance, spin and pump controllers required to solve this task. Switching density networks can be difficult to train, but we introduce a cross entropy regularisation loss that stabilises training.


page 4

page 6

page 7

page 8


From explanation to synthesis: Compositional program induction for learning from demonstration

Hybrid systems are a compact and natural mechanism with which to address...

Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation

The control of nonlinear dynamical systems remains a major challenge for...

NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spaces

Learning low-dimensional latent state space dynamics models has been a p...

Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning

This work considers two distinct settings: imitation learning and goal-c...

DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL

Many realistic robotics tasks are best solved compositionally, through c...

Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks

Partial Automation (PA) with intelligent support systems has been introd...

Global optimization for low-dimensional switching linear regression and bounded-error estimation

The paper provides global optimization algorithms for two particularly d...

Please sign up or login with your details

Forgot password? Click here to reset