Metraipolis › archive › dc_427a77a71ca3
Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties — arXiv:2610.20210
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20210
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T20:02:26.654Z
- SHA-256 of the archived text
3d4f4c4ab71f59444619b4e98cfb55e10a088ac38c40c016cf1d7a6d089f27ce- Stable URL of this page
https://metraipolis.com/documento/dc_427a77a71ca3
How to cite
Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties — arXiv:2610.20210 — arXiv (en), https://arxiv.org/abs/2610.20210 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_427a77a71ca3 (Metraipolis archive dc_427a77a71ca3, sha256 3d4f4c4ab71f59444619b4e98cfb55e10a088ac38c40c016cf1d7a6d089f27ce)
BibTeX
@misc{dc427a77a71ca3,
title = {Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties — arXiv:2610.20210},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20210},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_427a77a71ca3; sha256 3d4f4c4ab71f59444619b4e98cfb55e10a088ac38c40c016cf1d7a6d089f27ce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20210. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Counterfactual reasoning (asking what would have happened, had a decision been different) is a powerful tool for identifying causes of failure and explaining the behaviour of AI systems in sequential decision-making tasks. In Markov Decision Processes (MDPs), two sources of uncertainty complicate counterfactual inference: statistical uncertainty in the MDP transitions when the MDP is estimated from trajectory data, and uncertainty about the unknown causal model, as there are multiple structural causal models (SCMs) compatible with each MDP. Existing work addresses these two challenges in isolation. We address both simultaneously by introducing a framework for partial counterfactual inference in MDPs that is robust to both statistical and causal uncertainty. Our approach provides: 1) closed-form analytical bounds for the counterfactual probabilities that are valid across all SCMs entailed by a given interval MDP (IMDP); 2) a method to compute minimal robust interventions to achieve a desired counterfactual outcome via pessimistic value iteration on the induced counterfactual IMDP. Since the latter is constructed using our analytical bounds, our approach remains efficient and scalable to realistic MDP environments. Experiments across multiple case studies demonstrate our method's robustness and practical utility for identifying minimal sets of actions that, if changed, would have led to improved outcomes. 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/2610.20210 — 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 2026-10-15T19:35:48.298Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).