GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Major/Subject

Mcode

Degree programme

Language

en

Pages

25

Series

Artificial Intelligence, Volume 320

Abstract

Learning optimal control policies directly on physical systems is challenging. Even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. This work proposes GOSAFEOPT as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GOSAFEOPT over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.

Description

Other note

Citation

Sukhija, B, Turchetta, M, Lindner, D, Krause, A, Trimpe, S & Baumann, D 2023, 'GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems', Artificial Intelligence, vol. 320, 103922. https://doi.org/10.1016/j.artint.2023.103922