Metraipolis › archive › dc_f5c4815ea4ed

Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models — arXiv:2608.02893

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02893
License (as archived)
CC0-1.0
Archived
2026-10-31T12:18:21.666Z
SHA-256 of the archived text
286bcc34a504e770cff406d47dee18a17b52f2637217d987b6792502d2796b81
Stable URL of this page
https://metraipolis.com/documento/dc_f5c4815ea4ed

How to cite

Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models — arXiv:2608.02893 — arXiv (en), https://arxiv.org/abs/2608.02893 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f5c4815ea4ed (Metraipolis archive dc_f5c4815ea4ed, sha256 286bcc34a504e770cff406d47dee18a17b52f2637217d987b6792502d2796b81)
BibTeX
@misc{dcf5c4815ea4ed,
  title = {Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models — arXiv:2608.02893},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02893},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f5c4815ea4ed; sha256 286bcc34a504e770cff406d47dee18a17b52f2637217d987b6792502d2796b81},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02893. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Counterfactual inference approaches for sequential decision-making typically assume deterministic causal models, where all randomness stems from latent variables. However, Markov Decision Processes (MDPs) are inherently stochastic. We address this by formalising counterfactual policy optimisation under probabilistic nondeterministic causal models, which properly separates latent confounding from irreducible stochasticity, and here propose a first practical optimisation problem for identifying robust counterfactual policies under a sensitivity analysis framework. We validate our approach on a sepsis treatment simulator, where diabetes status acts as a hidden global confounder.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02893 — 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 2026-10-31T12:05:52.963Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).