Metraipolis › archive › dc_09da51b5cd92

DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes — arXiv:2611.00342

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00342
License (as archived)
CC0-1.0
Archived
2026-11-03T18:35:09.699Z
SHA-256 of the archived text
ac2792295cdad2786f73ccab542822dafe2ee74c5b6e69f8e71dafe19247a3c0
Stable URL of this page
https://metraipolis.com/documento/dc_09da51b5cd92

How to cite

DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes — arXiv:2611.00342 — arXiv (en), https://arxiv.org/abs/2611.00342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09da51b5cd92 (Metraipolis archive dc_09da51b5cd92, sha256 ac2792295cdad2786f73ccab542822dafe2ee74c5b6e69f8e71dafe19247a3c0)
BibTeX
@misc{dc09da51b5cd92,
  title = {DEPLOY-RL: Active Boundary Discovery and Conservative Certification for Deployable Reinforcement Learning in Safety-Critical Continuous Processes — arXiv:2611.00342},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00342},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09da51b5cd92; sha256 ac2792295cdad2786f73ccab542822dafe2ee74c5b6e69f8e71dafe19247a3c0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reinforcement learning (RL) policies often outperform classical controllers in simulation, yet rarely reach production in safety-critical processes. The barrier is that there is no principled way to answer "Is this policy safe to deploy?" with statistical guarantees. We introduce DEPLOY-RL, a post-training certification framework built on one key insight: deployment certification requires discovering where failures occur (boundary discovery), not measuring how much everywhere (uniform reconstruction). Our contributions: (1) a contract-coupled acquisition function that concentrates sampling on certification-critical boundaries, achieving approximately 2x sample efficiency with a semi-empirical ambiguity reduction bound (domain-calibrated convergence guarantee); (2) conformal risk control providing finite-sample false-go guarantees (<= alpha) under explicit deployment contracts; (3) a three-way decision framework (Deploy/No-Deploy/Abstain) with fail-safe PID/MPC fallback. In simulations on papermaking (industrial digital twin) and Tennessee Eastman (public benchmark), DEPLOY-RL achieves 4.4% false-go rate (vs. 8.6% for the best baseline) while retaining 88.6% policy coverage, the only method achieving <5% false-go with >85% coverage among 14 baselines under our evaluation protocol.

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/2611.00342 — 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 2026-11-03T18:12:54.412Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).