Holding a plasma in shape.
Researchers used reinforcement learning to control magnetic confinement in a research tokamak.
Original sources ↓ · Revision history ↓
Demonstrated · source published 2022-02-16
The human problem
Hot plasma must be controlled within a complex magnetic system.
The prior constraint
Controllers require specialized engineering for target configurations.
AI’s actual role
A trained policy commanded the tokamak’s magnetic coils.
The documented result
The controller demonstrated multiple plasma configurations on TCV.
Why it may matter
A tool for researchers exploring fusion reactor designs.
Limitations
Plasma control is not net energy production or commercial fusion.
Unresolved questions
Test broader conditions and more demanding devices.
Source history & evidence assessment
- Maturity
- Demonstrated
- Claim confidence
- unassessed
- Event date
- Not recorded
- Source published
- 2022-02-16
- Captured
- Not recorded
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- Lausanne, Switzerland · institution-location
Legacy source check; no named human reviewer is recorded in this projection.
Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.
Original sources
Magnetic control of tokamak plasmas through deep reinforcement learning ↗ · paper
Institutions: EPFL & DeepMind
Explore the underlying question
Related developments
Editorial connections between distinct settings and results; these links do not imply replication.
Revision & correction history
No corrections recorded.