Metraipolis › archive › dc_758cea170c85
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies — arXiv:2610.04418
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04418
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:31.908Z
- SHA-256 of the archived text
9b5f63231bb0c1ca21608f9f9bf2504ddfc6e5123130d9fef6e236ba9c471f1f- Stable URL of this page
https://metraipolis.com/documento/dc_758cea170c85
How to cite
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies — arXiv:2610.04418 — arXiv, https://arxiv.org/abs/2610.04418 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_758cea170c85 (Metraipolis archive dc_758cea170c85, sha256 9b5f63231bb0c1ca21608f9f9bf2504ddfc6e5123130d9fef6e236ba9c471f1f)
BibTeX
@misc{dc758cea170c85,
title = {CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies — arXiv:2610.04418},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04418},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_758cea170c85; sha256 9b5f63231bb0c1ca21608f9f9bf2504ddfc6e5123130d9fef6e236ba9c471f1f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04418. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objective specifications and robustness under real-world environmental drift. However, to protect intellectual property, the RL agent may be delivered for evaluation as opaque executable or remote API, which makes traditional evaluation techniques based on the internals of the policies infeasible. To address this gap, CORE-RL: Confidence-Oriented Reliability Evaluation of black box RL policy is proposed in this paper. The CORE-RL pipeline introduces a Unified Reliability Metric that formally integrates early task termination and safety constraint violations, preventing unsafe policies from masking failures through premature episode halts. By subjecting the policy to a noise certification envelope of perceptual noise, actuation noise and change in environment dynamics, the pipeline computes the finite-sample Clopper-Pearson bounds on unified reliability metric and Hoeffdings' lower bound on reward and safety cost. The pipeline then defines safe operational design domain to report high-confidence certificates for safety and expected performance. Experiments on continuous control tasks demonstrate the CORE-RL pipeline's ability to automatically reject non-compliant policies and map the safe Operational Design Domain (ODD) of safety-aware policies. Thus CORE-RL provides an evaluation framework towards a quantitative, transparent and reproducible, statistical rationale necessary to safely evaluate, compare, and deploy black box RL solutions. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.04418 — 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 2026-10-06T05:24:05.465Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).