Metraipolis › archive › dc_2e9d2a5fa3f8
Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization — arXiv:2610.09350
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09350
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:50.598Z
- SHA-256 of the archived text
6d49c07e65923694b9e04425ca814636c570c57836f1f3c40b90991bd003d56d- Stable URL of this page
https://metraipolis.com/documento/dc_2e9d2a5fa3f8
How to cite
Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization — arXiv:2610.09350 — arXiv (en), https://arxiv.org/abs/2610.09350 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e9d2a5fa3f8 (Metraipolis archive dc_2e9d2a5fa3f8, sha256 6d49c07e65923694b9e04425ca814636c570c57836f1f3c40b90991bd003d56d)
BibTeX
@misc{dc2e9d2a5fa3f8,
title = {Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization — arXiv:2610.09350},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09350},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e9d2a5fa3f8; sha256 6d49c07e65923694b9e04425ca814636c570c57836f1f3c40b90991bd003d56d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09350. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learning from demonstrations (LfD) provides a framework for inferring unknown constraints from locally optimal, constraint-satisfying expert behavior. Existing approaches largely fall into two paradigms, constrained inverse optimal control (CIOC) and inverse constrained reinforcement learning (ICRL). CIOC exploits optimality conditions such as the Karush--Kuhn--Tucker (KKT) conditions but typically assumes known dynamics and structured constraint representations. Meanwhile, ICRL accommodates complex unknown constraints and unknown transition dynamics but often requires extensive online exploration, during which unsafe constraint violations may occur. In this work, we introduce Counterfactual KKT (CF-KKT), a constraint learning framework that leverages learned dynamics and locally optimal demonstrations to recover unknown constraints without requiring known dynamics or additional risky exploration, thereby combining the data efficiency and safety advantages of CIOC with the flexibility of ICRL. First, we use a locally learned differentiable dynamics model to impose KKT-inspired optimality conditions directly on the demonstrations. Second, we use the learned dynamics to generate reward-improving counterfactual behaviors near the demonstrations, revealing behaviors that would be preferable in the absence of the unknown constraint and thus providing synthetic infeasible data. When the constraint parameterization is known, the same learned-dynamics framework enables direct CIOC-based parameter recovery, and we characterize its sensitivity to dynamics misspecification. Across high-dimensional robotic control tasks, our approach learns neural constraint representations with improved safety and data efficiency relative to state-of-the-art offline ICRL baselines. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.09350 — 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 2026-10-08T12:14:15.389Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).