Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mouchamps, Antoine, Malherbe, Arthur, Bolland, Adrien, Ernst, Damien
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.11283
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910060405325824
author Mouchamps, Antoine
Malherbe, Arthur
Bolland, Adrien
Ernst, Damien
author_facet Mouchamps, Antoine
Malherbe, Arthur
Bolland, Adrien
Ernst, Damien
contents This paper presents Gym-TORAX, a Python package enabling the implementation of Reinforcement Learning (RL) environments for simulating plasma dynamics and control in tokamaks. Users define succinctly a set of control actions and observations, and a control objective from which Gym-TORAX creates a Gymnasium environment that wraps TORAX for simulating the plasma dynamics. The objective is formulated through rewards depending on the simulated state of the plasma and control action to optimize specific characteristics of the plasma, such as performance and stability. The resulting environment instance is then compatible with a wide range of RL algorithms and libraries and will facilitate RL research in plasma control. In its current version, one environment is readily available, based on a ramp-up scenario of the International Thermonuclear Experimental Reactor (ITER).
format Preprint
id arxiv_https___arxiv_org_abs_2510_11283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gym-TORAX: Open-source software for integrating reinforcement learning with plasma control simulators in tokamak research
Mouchamps, Antoine
Malherbe, Arthur
Bolland, Adrien
Ernst, Damien
Machine Learning
This paper presents Gym-TORAX, a Python package enabling the implementation of Reinforcement Learning (RL) environments for simulating plasma dynamics and control in tokamaks. Users define succinctly a set of control actions and observations, and a control objective from which Gym-TORAX creates a Gymnasium environment that wraps TORAX for simulating the plasma dynamics. The objective is formulated through rewards depending on the simulated state of the plasma and control action to optimize specific characteristics of the plasma, such as performance and stability. The resulting environment instance is then compatible with a wide range of RL algorithms and libraries and will facilitate RL research in plasma control. In its current version, one environment is readily available, based on a ramp-up scenario of the International Thermonuclear Experimental Reactor (ITER).
title Gym-TORAX: Open-source software for integrating reinforcement learning with plasma control simulators in tokamak research
topic Machine Learning
url https://arxiv.org/abs/2510.11283