User: Guest  Login
Title:

A Robust Stability Approach to Robot Reinforcement Learning based on a Parameterization of Stabilizing Controllers

Document type:
Konferenzbeitrag
Contribution type:
Textbeitrag / Aufsatz
Author(s):
Friedrich, Stefan R.; Buss, Martin
Abstract:
Reinforcement learning has become more and more popular in robotics for acquiring feedback controllers. Many approaches aim for learning a controller from scratch, i.e., data-driven without any modeling of the physical plant. However, stability properties of the closed loop are often not considered, or established only a-posteriori or ad hoc. We propose to employ reinforcement learning in the context of model-based control, allowing to learn in a framework of stabilizing controllers built...     »
Keywords:
Adaptation models; Adaptive control; Learning (artificial intelligence); Robotcontrol; Stability analysis
Book / Congress title:
2017 IEEE International Conference on Robotics and Automation (ICRA)
Organization:
IEEE
Date of congress:
May 29 - June 3, 2017
Year:
2017
Month:
May
Pages:
3365-3372
Language:
en
Fulltext / DOI:
doi:10.1109/ICRA.2017.7989382
Semester:
SS 17
 BibTeX