Deep reinforcement learning controls fusion plasma in the TCV tokamak
Result confirmed
Importance: major (4 of 5)The takeaway
DeepMind and EPFL (Nature, Feb 2022) trained a single deep-RL policy in simulation that commanded all of TCV’s magnetic control coils on the real machine.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- Major (4 of 5)
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- Nature 602 (Feb 2022)
- Zero-shot sim-to-real transfer: trained in a simulator, deployed directly on the tokamak
- One neural controller replaced a set of hand-designed feedback loops for 19 magnetic coils
What happened
A neural network learned to steer a hot plasma by adjusting magnetic coils thousands of times per second, first in simulation and then on the real reactor.
Why it matters
It showed that RL could replace complex hand-engineered control in fusion devices and opened the way to AI-designed plasma scenarios.
Sources
2 sources from 2 sites. Numbers match the chips in the text.
2 sources: 2 primary
Primary
- Magnetic control of tokamak plasmas through deep reinforcement learning (Nature)nature.com, paper
- DeepMind: Accelerating fusion science through learned plasma controldeepmind.google, official
Changes
- Filed