From self-tuning regulators to reinforcement learning and back again

Nikolai Matni, Alexandre Proutiere, Anders Rantzer, Stephen Tu

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingForskningPeer review

5 Citeringar (SciVal)


Machine and reinforcement learning (RL) are increasingly being applied to plan and control the behavior of autonomous systems interacting with the physical world. Examples include self-driving vehicles, distributed sensor networks, and agile robots. However, when machine learning is to be applied in these new settings, the algorithms had better come with the same type of reliability, robustness, and safety bounds that are hallmarks of control theory, or failures could be catastrophic. Thus, as learning algorithms are increasingly and more aggressively deployed in safety critical settings, it is imperative that control theorists join the conversation. The goal of this tutorial paper is to provide a starting point for control theorists wishing to work on learning related problems, by covering recent advances bridging learning and control theory, and by placing these results within an appropriate historical context of system identification and adaptive control.

Titel på gästpublikation2019 IEEE 58th Conference on Decision and Control, CDC 2019
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Antal sidor17
ISBN (elektroniskt)9781728113982
ISBN (tryckt)978-1-7281-1399-9
StatusPublished - 2020 mar 12
Evenemang58th IEEE Conference on Decision and Control, CDC 2019 - Nice, Frankrike
Varaktighet: 2019 dec 112019 dec 13


NamnProceedings of the IEEE Conference on Decision and Control
ISSN (tryckt)0743-1546
ISSN (elektroniskt)2576-2370


Konferens58th IEEE Conference on Decision and Control, CDC 2019

Ämnesklassifikation (UKÄ)

  • Reglerteknik


Utforska forskningsämnen för ”From self-tuning regulators to reinforcement learning and back again”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här