Tokamak Plasma Magnetic Confinement Control
Controllers were trained in simulation on a tokamak model and then deployed on the real device, shaping the plasma by commanding magnetic coils in real time - including demanding configurations such as the double snowflake.
Why it matters for industry: It demonstrates the full loop that engineering teams care about: physics-based simulator for training, sim-to-real transfer, and real-time closed-loop control on hardware.
Tags: FusionReinforcement LearningControlPlasmaEnergy
Related entries
- HydroGym: A Reinforcement Learning Platform for Flow Control · An open-source reinforcement learning platform for flow control that couples six
- Physics-Informed CNN for Battery Pack Temperature Fields · A physics-informed convolutional neural network whose loss encodes the finite-di
- MACE-MP-0: A Universal Machine-Learned Interatomic Potential · A general-purpose machine-learned interatomic potential built on an equivariant
- TopoDiff: Diffusion-Model-Driven Topology Optimization · A conditional diffusion approach to structural topology optimization from MIT th
- How to Use AI Agents to Prepare 3D Scenes for Simulation · This NVIDIA blog post describes how agentic AI workflows can be used to prepare