Metraipolis › archive › dc_4797fb2849ed
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions — arXiv:2608.26755
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26755
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:12:21.723Z
- SHA-256 of the archived text
21ef016ec06929f31c05f135633e1f8a2a805a98f4eea05321be5654b5990fa2- Stable URL of this page
https://metraipolis.com/documento/dc_4797fb2849ed
How to cite
Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions — arXiv:2608.26755 — arXiv (en), https://arxiv.org/abs/2608.26755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4797fb2849ed (Metraipolis archive dc_4797fb2849ed, sha256 21ef016ec06929f31c05f135633e1f8a2a805a98f4eea05321be5654b5990fa2)
BibTeX
@misc{dc4797fb2849ed,
title = {Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions — arXiv:2608.26755},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26755},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4797fb2849ed; sha256 21ef016ec06929f31c05f135633e1f8a2a805a98f4eea05321be5654b5990fa2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, recommendation systems, and autonomous systems. Safety is central in many of these applications, since a single unsafe decision in settings such as dosage selection or autonomous driving can have catastrophic consequences. A common way to model safety in bandit problems is to associate each action with both a reward signal and a cost signal, and to optimize reward subject to constraints on cost. Most existing safety-constrained bandit models enforce safety by requiring the expected cost of each action to remain below a prescribed threshold. However, this may be insufficient in heteroscedastic settings, where the chosen action affects not only the expected reward and cost, but also the variability of the observed outcomes. We study contextual bandits with one-dimensional continuous actions and stage-wise high-probability constraints on the realized cost. We propose High-Probability Constrained UCB, an optimistic-pessimistic algorithm that explores for reward while conservatively estimating the safe action set. For linear reward and cost models, we prove a tight $\tilde{\mathcal{O}}(d\sqrt{T})$ regret bound, and we extend the analysis to general function classes using the eluder dimension. Experiments show that enforcing realized-cost safety substantially reduces violations compared with expected-cost constrained baselines.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.26755 — 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 2026-10-17T15:34:49.924Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).