EconPapers    
Economics at your fingertips  
 

Magnetic control of tokamak plasmas through deep reinforcement learning

Jonas Degrave, Federico Felici (), Jonas Buchli (), Michael Neunert, Brendan Tracey (), Francesco Carpanese, Timo Ewalds, Roland Hafner, Abbas Abdolmaleki, Diego de las Casas, Craig Donner, Leslie Fritz, Cristian Galperti, Andrea Huber, James Keeling, Maria Tsimpoukelli, Jackie Kay, Antoine Merle, Jean-Marc Moret, Seb Noury, Federico Pesamosca, David Pfau, Olivier Sauter, Cristian Sommariva, Stefano Coda, Basil Duval, Ambrogio Fasoli, Pushmeet Kohli, Koray Kavukcuoglu, Demis Hassabis and Martin Riedmiller
Additional contact information
Jonas Degrave: DeepMind
Federico Felici: Swiss Plasma Center - EPFL
Jonas Buchli: DeepMind
Michael Neunert: DeepMind
Brendan Tracey: DeepMind
Francesco Carpanese: DeepMind
Timo Ewalds: DeepMind
Roland Hafner: DeepMind
Abbas Abdolmaleki: DeepMind
Diego de las Casas: DeepMind
Craig Donner: DeepMind
Leslie Fritz: DeepMind
Cristian Galperti: Swiss Plasma Center - EPFL
Andrea Huber: DeepMind
James Keeling: DeepMind
Maria Tsimpoukelli: DeepMind
Jackie Kay: DeepMind
Antoine Merle: Swiss Plasma Center - EPFL
Jean-Marc Moret: Swiss Plasma Center - EPFL
Seb Noury: DeepMind
Federico Pesamosca: Swiss Plasma Center - EPFL
David Pfau: DeepMind
Olivier Sauter: Swiss Plasma Center - EPFL
Cristian Sommariva: Swiss Plasma Center - EPFL
Stefano Coda: Swiss Plasma Center - EPFL
Basil Duval: Swiss Plasma Center - EPFL
Ambrogio Fasoli: Swiss Plasma Center - EPFL
Pushmeet Kohli: DeepMind
Koray Kavukcuoglu: DeepMind
Demis Hassabis: DeepMind
Martin Riedmiller: DeepMind

Nature, 2022, vol. 602, issue 7897, 414-419

Abstract: Abstract Nuclear fusion using magnetic confinement, in particular in the tokamak configuration, is a promising path towards sustainable energy. A core challenge is to shape and maintain a high-temperature plasma within the tokamak vessel. This requires high-dimensional, high-frequency, closed-loop control using magnetic actuator coils, further complicated by the diverse requirements across a wide range of plasma configurations. In this work, we introduce a previously undescribed architecture for tokamak magnetic controller design that autonomously learns to command the full set of control coils. This architecture meets control objectives specified at a high level, at the same time satisfying physical and operational constraints. This approach has unprecedented flexibility and generality in problem specification and yields a notable reduction in design effort to produce new plasma configurations. We successfully produce and control a diverse set of plasma configurations on the Tokamak à Configuration Variable1,2, including elongated, conventional shapes, as well as advanced configurations, such as negative triangularity and ‘snowflake’ configurations. Our approach achieves accurate tracking of the location, current and shape for these configurations. We also demonstrate sustained ‘droplets’ on TCV, in which two separate plasmas are maintained simultaneously within the vessel. This represents a notable advance for tokamak feedback control, showing the potential of reinforcement learning to accelerate research in the fusion domain, and is one of the most challenging real-world systems to which reinforcement learning has been applied.

Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (17)

Downloads: (external link)
https://www.nature.com/articles/s41586-021-04301-9 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:602:y:2022:i:7897:d:10.1038_s41586-021-04301-9

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-021-04301-9

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().

 
Page updated 2025-03-19
Handle: RePEc:nat:nature:v:602:y:2022:i:7897:d:10.1038_s41586-021-04301-9