Hybrid system identification using switching density networks

Michael Burke, Yordan Hristov, Subramanian Ramamoorthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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.
Original languageEnglish
Title of host publicationProceedings of the Conference on Robot Learning 2019
Number of pages10
Publication statusPublished - 2020
EventConference on Robot Learning (CoRL) - 2019 Edition - Osaka, Japan
Duration: 30 Oct 20191 Nov 2019

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


ConferenceConference on Robot Learning (CoRL) - 2019 Edition
Abbreviated titleCoRL 2019
Internet address


Dive into the research topics of 'Hybrid system identification using switching density networks'. Together they form a unique fingerprint.

Cite this