Active ramp-down control and trajectory design for tokamaks with neural differential equations and reinforcement learning

Abstract The tokamak offers a promising path to fusion energy, but disruptions pose a major economic risk, motivating solutions to manage their consequence. This work develops a reinforcement learning approach to this problem by training a policy to ramp-down the plasma current while avoiding limits...

Full description

Saved in:
Bibliographic Details
Main Authors: Allen M. Wang, Cristina Rea, Oswin So, Charles Dawson, Darren T. Garnier, Chuchu Fan
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Communications Physics
Online Access:https://doi.org/10.1038/s42005-025-02146-6
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract The tokamak offers a promising path to fusion energy, but disruptions pose a major economic risk, motivating solutions to manage their consequence. This work develops a reinforcement learning approach to this problem by training a policy to ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed. To address physics uncertainty and model inaccuracies, the simulation is massively parallelized on GPU with randomized physics parameters during policy training. The trained policy is then run in feedback on a transport simulator as a demonstration. We also directly address the crucial issue of control validation by demonstrating that a constraint-conditioned policy can be a trajectory design assistant that designs a library of feed-forward trajectories to handle different physics conditions and user constraint settings, a promising approach for the sensitive context of burning plasma tokamaks. Finally, we demonstrate that the training environment can be a useful platform for feed-forward optimization approaches by optimizing feed-forward trajectories that are robust to physics uncertainty.
ISSN:2399-3650