From self-tuning regulators to reinforcement learning and back again
Matni, Nikolai ; Proutiere, Alexandre ; Rantzer, Anders LU
and Tu, Stephen
(2020)
58th IEEE Conference on Decision and Control, CDC 2019
In Proceedings of the IEEE Conference on Decision and Control
2019-December.
p.3724-3740
- Abstract
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... (More)
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.
(Less)
- author
- Matni, Nikolai
; Proutiere, Alexandre
; Rantzer, Anders
LU
and Tu, Stephen
- organization
- publishing date
- 2020-03-12
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2019 IEEE 58th Conference on Decision and Control, CDC 2019
- series title
- Proceedings of the IEEE Conference on Decision and Control
- volume
- 2019-December
- article number
- 9029916
- pages
- 17 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 58th IEEE Conference on Decision and Control, CDC 2019
- conference location
- Nice, France
- conference dates
- 2019-12-11 - 2019-12-13
- external identifiers
-
- scopus:85082464185
- ISSN
- 0743-1546
- 2576-2370
- ISBN
- 978-1-7281-1399-9
- 9781728113982
- DOI
- 10.1109/CDC40024.2019.9029916
- project
- WASP: Wallenberg AI, Autonomous Systems and Software Program at Lund University
- Scalable Control of Interconnected Systems
- language
- English
- LU publication?
- yes
- id
- ecdfda58-fc78-424f-8fad-7738edfa5b69
- alternative location
- https://arxiv.org/abs/1906.11392
- date added to LUP
- 2020-04-29 15:38:57
- date last changed
- 2024-05-29 11:46:42
@inproceedings{ecdfda58-fc78-424f-8fad-7738edfa5b69,
abstract = {{<p>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.</p>}},
author = {{Matni, Nikolai and Proutiere, Alexandre and Rantzer, Anders and Tu, Stephen}},
booktitle = {{2019 IEEE 58th Conference on Decision and Control, CDC 2019}},
isbn = {{978-1-7281-1399-9}},
issn = {{0743-1546}},
language = {{eng}},
month = {{03}},
pages = {{3724--3740}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{Proceedings of the IEEE Conference on Decision and Control}},
title = {{From self-tuning regulators to reinforcement learning and back again}},
url = {{http://dx.doi.org/10.1109/CDC40024.2019.9029916}},
doi = {{10.1109/CDC40024.2019.9029916}},
volume = {{2019-December}},
year = {{2020}},
}