Deep reinforcement learning controls tokamak fusion plasma
A reinforcement-learning controller learned to shape and stabilise the magnetic confinement of real fusion plasma inside the TCV tokamak, holding configurations that are hard to sustain by hand.
- Model
- DeepMind RL controller
- Field
- Physics
- Date
- 2022-02-16
What was found
Working with EPFL's Swiss Plasma Center, DeepMind trained a deep reinforcement-learning agent to command the magnetic control coils of the TCV tokamak. Learning in a simulator against specified target shapes, the controller then ran on the real machine, holding elongated, snowflake and other configurations, including a 'droplet' state with two separate plasmas at once. It is one of the first times a single learned controller replaced the hand-engineered cascade normally required.
Novelty check
Magnetic plasma control is normally built from many separately engineered controllers. A single RL-learned controller running on a real tokamak was new; the Nature paper documents the comparison against conventional control.
Caveats and known objections
Demonstrated on the TCV research tokamak, not a power-producing reactor, and the policy was trained in simulation before transfer to hardware. This is a control-engineering advance, not a solution to fusion energy. Independent groups have since extended RL plasma control to other machines.
Nobody outside the lab has checked this yet.
Reading the primary source closely enough to say whether it supports the claim counts as a check, and you are credited on the entry.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
Entry history (1 event)
- AddedEntered the registry graded Peer reviewed and Search scaffold.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Community discussion
Graded peer reviewed for verification and search scaffold for autonomy. What these mean.
Cite this entry
whataifound.org. (2022). Deep reinforcement learning controls tokamak fusion plasma. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2022-02-16-tokamak-plasma-controlBibTeX
@misc{whataifound-googledeepmind-2022-control,
title = {Deep reinforcement learning controls tokamak fusion plasma},
author = {{whataifound.org}},
year = {2022},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by Google DeepMind. Verification: Peer reviewed. Autonomy: Search scaffold.},
url = {https://whataifound.org/finding/2022-02-16-tokamak-plasma-control}
}