Provably Safe Reinforcement Learning via Action Projection Using Reachability Analysis and Polynomial Zonotopes

While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems. In this work, we address this issue by a safety shield for nonlinear continuous systems that solve reach-avoi...

Полное описание

Библиографические подробности

Главные авторы:	Niklas Kochdumper, Hanna Krasowski, Xiao Wang, Stanley Bak, Matthias Althoff
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2023-01-01
Серии:	IEEE Open Journal of Control Systems
Предметы:	Action projection reach-avoid problems reachability analysis reinforcement learning
Online-ссылка:	https://ieeexplore.ieee.org/document/10068193/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!