Safe reinforcement learning in uncertain contexts
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Authors
Date
2024
Major/Subject
Mcode
Degree programme
Language
en
Pages
14
Series
IEEE Transactions on Robotics, Volume 40, pp. 1828-1841
Abstract
When deploying machine learning algorithms in the real world, guaranteeing safety is an essential asset. Existing safe learning approaches typically consider continuous variables, i.e., regression tasks. However, in practice, robotic systems are also subject to discrete, external environmental changes, e.g., having to carry objects of certain weights or operating on frozen, wet, or dry surfaces. Such influences can be modeled as discrete context variables. In the existing literature, such contexts are, if considered, mostly assumed to be known. In this work, we drop this assumption and show how we can perform safe learning when we cannot directly measure the context variables. To achieve this, we derive frequentist guarantees for multiclass classification, allowing us to estimate the current context from measurements. Furthermore, we propose an approach for identifying contexts through experiments. We discuss under which conditions we can retain theoretical guarantees and demonstrate the applicability of our algorithm on a Furuta pendulum with camera measurements of different weights that serve as contexts.Description
Keywords
multiclass classification, safe reinforcement learning, Frequentist bounds
Other note
Citation
Baumann, D & Schön, T B 2024, ' Safe reinforcement learning in uncertain contexts ', IEEE Transactions on Robotics, vol. 40, pp. 1828-1841 . https://doi.org/10.1109/TRO.2024.3354176