Metraipolis › archive › dc_3ef8e7b45b97

Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant? — arXiv:2610.06211

Source
arXiv
Original
https://arxiv.org/abs/2610.06211
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:30.221Z
SHA-256 of the archived text
3ca0fb1db0e083e03d9909c7d7ba697af6bba799153ece49b22e231de22b6fa4
Stable URL of this page
https://metraipolis.com/documento/dc_3ef8e7b45b97

How to cite

Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant? — arXiv:2610.06211 — arXiv, https://arxiv.org/abs/2610.06211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ef8e7b45b97 (Metraipolis archive dc_3ef8e7b45b97, sha256 3ca0fb1db0e083e03d9909c7d7ba697af6bba799153ece49b22e231de22b6fa4)
BibTeX
@misc{dc3ef8e7b45b97,
  title = {Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant? — arXiv:2610.06211},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06211},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ef8e7b45b97; sha256 3ca0fb1db0e083e03d9909c7d7ba697af6bba799153ece49b22e231de22b6fa4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learned models for industrial control are usually judged by aggregate accuracy, but accuracy at the component level does not guarantee safety once it is embedded in the system it is meant to serve. We study this gap on a behavior-cloning task: imitating an expert Nonlinear Model Predictive Control (NMPC) policy for load-following of a Pressurized Water Reactor (PWR), an industrial system with tight safety constraints. We propose a structured architecture encoding variables from each timescale into separate latent spaces, reflecting the physical decomposition of the system, before training a controller to imitate the expert on the product latent space. On long-horizon rollouts, separated embeddings improve both accuracy and feasibility compared with a shared-embedding baseline. Sensitivity analysis further shows that our model yields interpretable representations aligned with the system's physics. However, standalone deployment still leaves several percent of trajectories infeasible regardless of the architecture. Using our method to warmstart the NMPC optimizer rather than acting standalone, we recover full feasibility and near-optimal cost while still cutting computation time by $\sim$15% relative to the expert controller, and even more for abrupt operating changes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06211 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:27:05.864Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).