Metraipolis › archive › dc_c2f45823e6c8
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation — arXiv:2608.24146
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24146
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:36:07.095Z
- SHA-256 of the archived text
9161dc48930aa16c674948ef7d1c039a064fc3a12c4f4a17bd677e13c335b082- Stable URL of this page
https://metraipolis.com/documento/dc_c2f45823e6c8
How to cite
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation — arXiv:2608.24146 — arXiv (en), https://arxiv.org/abs/2608.24146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2f45823e6c8 (Metraipolis archive dc_c2f45823e6c8, sha256 9161dc48930aa16c674948ef7d1c039a064fc3a12c4f4a17bd677e13c335b082)
BibTeX
@misc{dcc2f45823e6c8,
title = {Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation — arXiv:2608.24146},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24146},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2f45823e6c8; sha256 9161dc48930aa16c674948ef7d1c039a064fc3a12c4f4a17bd677e13c335b082},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting policies tailored to reduce online evaluation variance. However, these approaches do not account for uncertainties in the transition functions. In practice, simulator transitions often differ from the real world due to modeling errors or approximation limitations. As a result, behavior policies trained in simulation may still yield high variance when deployed in real environments, leading to costly reliance on real-world evaluation samples. In this work, we propose a double-loop gradient-based algorithm for learning behavior policies that are both efficient and robust to transition uncertainty. Theoretically, we derive novel transition-variance gradient expressions and establish global convergence guarantees for the algorithm. Numerically, we demonstrate that our method is less sensitive to transition perturbations than existing approaches, providing supportive evidence for its practical utility. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2608.24146 — 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 2026-10-18T06:28:52.231Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).