Metraipolis › archive › dc_ce6ca6100c79

From Privileged Control to Deployable Adaptation:Fusing Mechanism-Guided Task Reduction with Learned Behavior — arXiv:2608.10453

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10453
License (as archived)
CC0-1.0
Archived
2026-10-19T06:48:17.376Z
SHA-256 of the archived text
277d3eb15632e7fafca9297355a3a8e995b0e5abf9ca8b2244b5c78d27474471
Stable URL of this page
https://metraipolis.com/documento/dc_ce6ca6100c79

How to cite

From Privileged Control to Deployable Adaptation:Fusing Mechanism-Guided Task Reduction with Learned Behavior — arXiv:2608.10453 — arXiv (en), https://arxiv.org/abs/2608.10453 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce6ca6100c79 (Metraipolis archive dc_ce6ca6100c79, sha256 277d3eb15632e7fafca9297355a3a8e995b0e5abf9ca8b2244b5c78d27474471)
BibTeX
@misc{dcce6ca6100c79,
  title = {From Privileged Control to Deployable Adaptation:Fusing Mechanism-Guided Task Reduction with Learned Behavior — arXiv:2608.10453},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10453},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce6ca6100c79; sha256 277d3eb15632e7fafca9297355a3a8e995b0e5abf9ca8b2244b5c78d27474471},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10453. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simultaneous input-gain variation and large additive disturbance create a control problem in which a fixed observer or nominal controller may be unable to reproduce the performance of a regime-aware design. We study a training--deployment asymmetry: during simulation or commissioning, an expert controller is allowed to use the known gain and disturbance, whereas the deployed controller can use only the reference and measured states. Directly imitating expert actions is generally unsafe because the same instantaneous student observation may correspond to different privileged regimes and hence different expert actions. We propose a mechanism-guided transfer route rather than a new neural architecture. An exact sampled-data identity removes the additive disturbance from the expert law and reduces learning to a task-relevant inverse input gain inferred from causal state history. The latent target is reconstructed from expert actions and deployment-visible trajectories, so the true plant parameter is not required as a student label. A common-quadratic certificate is derived for the actual augmented sampled recursion, followed by explicit residual, coverage, switching, noise, and saturation qualifications. A parameter-regime scan shows that the nominal observer's error grows sharply as $a$ decreases and that the next gain above the best non-failing tuning diverges for every tested $a<1$. Direct action networks also fail in closed loop despite moderate offline error, whereas the structured student remains close to the privileged expert and reduces tracking RMSE by about 69\% relative to the tuned observer in unseen 60-s trials. The contribution is an interpretable design perspective for turning privileged multi-regime control knowledge into a deployable adaptive controller, together with conditions under which the transfer is meaningful.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-12 in eess.SY).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2608.10453 — 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 2026-10-19T06:41:52.233Z dalla pagina https://arxiv.org/catchup/eess.SY/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).