{
  "abstract": "Scenario development, the design of the waveforms that take a tokamak discharge from breakdown to flat-top, is still an iterative, labour-intensive process. Every candidate scenario has to be simulated with a controller in the loop, and the classical shape and current controllers need low-level actuator references. So the process is iterative and includes a number of trial-and-error steps. We propose to replace the per-scenario controller tuning by a single goal-conditioned reinforcement-learning controller trained once, in advance, against a free-boundary equilibrium and transport simulator. A scenario is then specified only by the target waveforms of the physical quantities of interest (plasma current, line-averaged electron density, LCFS shape, x-point positions), and the controller produces the coil-current and fueling commands that realize them. We demonstrate the approach on an EAST plasma-current ramp-up: the controller takes over a small limited plasma, ramps the current and the density, grows the cross-section, forms two x-points and holds a double-null diverted configuration against sampled shape targets for the rest of a 1.2 s episode. The neural network controller is trained using TQC algorithm. On 1024 test scenarios sampled from a low-discrepancy scrambled Sobol sequence in 11-dimensional target space, the controller forms the divertor in 86% of the cases, holds it for more than 0.5 s in 67% and reaches the end of the episode in a diverted state in 58%, with flat-top tracking errors of a few kA in plasma current, $\\sim 0.15\\times10^{19}$ m$^{-3}$ in density, $\\sim 2$ cm in position and $\\sim 8$ cm in x-point location; the failures concentrate at the high-current density ($J$) region which is believed to be physically or from engineering perspective not feasible within ohmic mode.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.26138",
  "author_total": 8,
  "authors": [
    {
      "name": "Evgeny Adishchev"
    },
    {
      "name": "Maxim Nurgaliev"
    },
    {
      "name": "Dmitry Sorokin"
    },
    {
      "name": "Alexander Granovsky"
    },
    {
      "name": "Maksim Stokolesov"
    },
    {
      "name": "Igor Prokofyev"
    },
    {
      "name": "Eduard Khairutdinov"
    },
    {
      "name": "Georgy Subbotin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c2x5hn8gvm8xt.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.26138",
  "fulltext_url": null,
  "id": "c2x5hn8gvm8xt",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.26138",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.plasm-ph"
    ],
    [
      "openalex",
      "3106|Magnetic confinement fusion research"
    ]
  ],
  "openalex": "W7223025664",
  "pdf_url": "https://arxiv.org/pdf/2610.26138",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c2x5hn8gvm8xt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:30:52Z",
      "native_id": "2610.26138",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.26138"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.plasm-ph",
      "subfield": "plasma"
    }
  ],
  "title": "Reinforcement Learning Controllers for Fusion Scenario Development",
  "title_text": "Reinforcement Learning Controllers for Fusion Scenario Development",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:41Z",
  "url": "https://research.draconitic.com/paper/c2x5hn8gvm8xt",
  "venue": "arXiv",
  "versions": []
}