Avoiding fusion plasma tearing instability with deep reinforcement learning

Abstract For stable and efficient fusion energy production using a tokamak reactor, it is essential to maintain a high-pressure hydrogenic plasma without plasma disruption. Therefore, it is necessary to actively control the tokamak based on the observed plasma state, to manoeuvre high-pressure plasma while avoiding tearing instability, the leading cause of disruptions. This presents an obstacle-avoidance problem for which artificial intelligence based on reinforcement learning has recently shown remarkable performance 1–4 . However, the obstacle here, the tearing instability, is difficult to forecast and is highly prone to terminating plasma operations, especially in the ITER baseline scenario. Previously, we…

• UD
  U.S. Department of Energy

  Awards: AC02-09CH11466, DE-FC02-04ER54698, DE-AC02, FC02-04ER54698, DE-AC02-
• NR
  National Research Foundation
• NR
  National Research Foundation of Korea

  Award: RS-2023-00255492
• MO
  Ministry of Science and ICT, South Korea
• OO
  Office of Science

  Awards: DE-AC02-09CH11466, DE-FC02-04ER54698, DE-AC02
• FE
  Fusion Energy Sciences

  Awards: AC02-09CH11466, DE-FC02-04ER54698, DE-AC02-09CH11466, FC02-04ER54698