Metraipolis › archive › dc_cf963993fc57
Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making — arXiv:2608.17574
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17574
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:28:43.350Z
- SHA-256 of the archived text
da6e42f7d5539066e7fc87d024dd494a3a9d8571a5db112c2b091e91675a30dd- Stable URL of this page
https://metraipolis.com/documento/dc_cf963993fc57
How to cite
Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making — arXiv:2608.17574 — arXiv (en), https://arxiv.org/abs/2608.17574 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf963993fc57 (Metraipolis archive dc_cf963993fc57, sha256 da6e42f7d5539066e7fc87d024dd494a3a9d8571a5db112c2b091e91675a30dd)
BibTeX
@misc{dccf963993fc57,
title = {Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making — arXiv:2608.17574},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17574},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf963993fc57; sha256 da6e42f7d5539066e7fc87d024dd494a3a9d8571a5db112c2b091e91675a30dd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17574. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
How cautious should an agent be while it is still learning its environment? We propose RATTL (Risk-Adversarial Total-Reward Learning), which ties caution to epistemic uncertainty: the agent holds a Bayesian posterior over unknown dynamics and plans against a Wasserstein ambiguity set whose radius is a monotone function of that posterior. The radius contracts with evidence, so behaviour interpolates continuously between worst-case robustness and risk-neutral total-reward maximization. The design follows the duality underlying the Entropic Value-at-Risk, which converts the choice of a risk level into the choice of an ambiguity radius. We show the resulting planning problem is well posed under transience and compactness conditions, and prove a Safety Sandwich: the RATTL value lies between the uninformed robust value and the full- knowledge optimum, with a gap that vanishes as the posterior concentrates. In a canonical binary-hazard instance, the induced criterion reduces to Conditional Value-at-Risk at a level set by the posterior entropy. A worked example shows the agent deferring the efficient action until a sharp identification threshold. RATTL targets runtime safety for agents, including LLM-based systems, acting under uncertainty. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2608.17574 — 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 2026-10-18T14:27:54.279Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).