[HTML][HTML] Magnetic control of tokamak plasmas through deep reinforcement learning

J Degrave, F Felici, J Buchli, M Neunert, B Tracey… - Nature, 2022 - nature.com
Nuclear fusion using magnetic confinement, in particular in the tokamak configuration, is a
promising path towards sustainable energy. A core challenge is to shape and maintain a …

Multi-agent reinforcement learning: Methods, applications, visionary prospects, and challenges

Z Zhou, G Liu, Y Tang - arxiv preprint arxiv:2305.10091, 2023 - arxiv.org
Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI)
technique. However, current studies and applications need to address its scalability, non …

Machine learning and Bayesian inference in nuclear fusion research: an overview

A Pavone, A Merlo, S Kwak… - Plasma Physics and …, 2023 - iopscience.iop.org
This article reviews applications of Bayesian inference and machine learning (ML) in
nuclear fusion research. Current and next-generation nuclear fusion experiments require …

Reinforcement learning-trained optimisers and Bayesian optimisation for online particle accelerator tuning

J Kaiser, C Xu, A Eichler, A Santamaria Garcia… - Scientific reports, 2024 - nature.com
Online tuning of particle accelerators is a complex optimisation problem that continues to
require manual intervention by experienced human operators. Autonomous tuning is a …

Avoiding fusion plasma tearing instability with deep reinforcement learning

J Seo, SK Kim, A Jalalvand, R Conlin, A Rothstein… - Nature, 2024 - nature.com
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 …

Solving real-world optimization tasks using physics-informed neural computing

J Seo - Scientific Reports, 2024 - nature.com
Optimization tasks are essential in modern engineering fields such as chip design,
spacecraft trajectory determination, and reactor scenario development. Recently, machine …

PID-inspired inductive biases for deep reinforcement learning in partially observable control tasks

I Char, J Schneider - Advances in Neural Information …, 2023 - proceedings.neurips.cc
Deep reinforcement learning (RL) has shown immense potential for learning to control
systems through data alone. However, one challenge deep RL faces is that the full state of …

Development of an operation trajectory design algorithm for control of multiple 0D parameters using deep reinforcement learning in KSTAR

J Seo, YS Na, B Kim, CY Lee, MS Park, SJ Park… - Nuclear …, 2022 - iopscience.iop.org
This work develops an artificially intelligent (AI) tokamak operation design algorithm that
provides an adequate operation trajectory to control multiple plasma parameters …

A comprehensive study of various regressions and deep learning approaches for the prediction of friction factor in mobile bed channels

A Bassi, AA Mir, B Kumar, M Patel - Journal of Hydroinformatics, 2023 - iwaponline.com
A fundamental issue in the hydraulics of movable bed channels is the measurement of
friction factor (λ), which represents the head loss because of hydraulic resistance. The …

Offline model-based reinforcement learning for tokamak control

I Char, J Abbate, L Bardóczi, M Boyer… - … for Dynamics and …, 2023 - proceedings.mlr.press
Control for tokamaks, the leading candidate technology for nuclear fusion, is an important
pursuit since the realization of nuclear fusion as an energy source would result in virtually …