Metraipolis › archive › dc_5125485bb2a8
Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation — arXiv:2610.40056
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40056
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:27:19.756Z
- SHA-256 of the archived text
27fc4f01ba8790e3d0f8d3b1c5b1953ad6f7bc967c391bd4168e780766a9abf2- Stable URL of this page
https://metraipolis.com/documento/dc_5125485bb2a8
How to cite
Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation — arXiv:2610.40056 — arXiv (en), https://arxiv.org/abs/2610.40056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5125485bb2a8 (Metraipolis archive dc_5125485bb2a8, sha256 27fc4f01ba8790e3d0f8d3b1c5b1953ad6f7bc967c391bd4168e780766a9abf2)
BibTeX
@misc{dc5125485bb2a8,
title = {Reinforcement Learning Under Runtime Confounding: Policy Learning and Off-Policy Evaluation — arXiv:2610.40056},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40056},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5125485bb2a8; sha256 27fc4f01ba8790e3d0f8d3b1c5b1953ad6f7bc967c391bd4168e780766a9abf2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reinforcement learning (RL) is increasingly used to train robust, adaptable systems across healthcare, e-commerce, and robotics. In these settings, legal, ethical, or logistical concerns may preclude certain key variables that drive decisions from being collected during deployment time. This gives rise to a setting known as runtime confounding: the logged data hold full observability, but deployment time lacks knowledge of certain variables, known as runtime confounders. Unlike single timepoint and non-adaptive settings, runtime confounding under reinforcement learning has the potential to propagate over time, as earlier decisions affect future states, observations, and action assignments, leading to biased learning. We address these problems with three contributions: we (1) develop policy learning algorithms under runtime-confounding, (2) develop semi-parametric efficient off-policy estimation procedures, and (3) provide diagnostics for understanding the price of runtime confounding. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2610.40056 — 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 2026-11-01T02:12:44.319Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).