IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2510.19672.html
   My bibliography  Save this paper

Policy Learning with Abstention

Author

Listed:
  • Ayush Sawarni
  • Jikai Jin
  • Justin Whitehouse
  • Vasilis Syrgkanis

Abstract

Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in high-stakes settings. We study policy learning with abstention, where a policy may defer to a safe default or an expert. When a policy abstains, it receives a small additive reward on top of the value of a random guess. We propose a two-stage learner that first identifies a set of near-optimal policies and then constructs an abstention rule from their disagreements. We establish fast O(1/n)-type regret guarantees when propensities are known, and extend these guarantees to the unknown-propensity case via a doubly robust (DR) objective. We further show that abstention is a versatile tool with direct applications to other core problems in policy learning: it yields improved guarantees under margin conditions without the common realizability assumption, connects to distributionally robust policy learning by hedging against small data shifts, and supports safe policy improvement by ensuring improvement over a baseline policy with high probability.

Suggested Citation

  • Ayush Sawarni & Jikai Jin & Justin Whitehouse & Vasilis Syrgkanis, 2025. "Policy Learning with Abstention," Papers 2510.19672, arXiv.org, revised Nov 2025.
    • Handle: RePEc:arx:papers:2510.19672
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2510.19672
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Keisuke Hirano & Jack R. Porter, 2009. "Asymptotics for Statistical Treatment Rules," Econometrica, Econometric Society, vol. 77(5), pages 1683-1701, September.
    2. Victor Chernozhukov & Denis Chetverikov & Mert Demirer & Esther Duflo & Christian Hansen & Whitney Newey & James Robins, 2018. "Double/debiased machine learning for treatment and structural parameters," Econometrics Journal, Royal Economic Society, vol. 21(1), pages 1-68, February.
    3. Erica E. M. Moodie & Thomas S. Richardson & David A. Stephens, 2007. "Demystifying Optimal Dynamic Treatment Regimes," Biometrics, The International Biometric Society, vol. 63(2), pages 447-455, June.
    4. Toru Kitagawa & Aleksey Tetenov, 2018. "Who Should Be Treated? Empirical Welfare Maximization Methods for Treatment Choice," Econometrica, Econometric Society, vol. 86(2), pages 591-616, March.
    5. Dylan J. Foster & Vasilis Syrgkanis, 2019. "Orthogonal Statistical Learning," Papers 1901.09036, arXiv.org, revised Jun 2023.
    6. Charles F. Manski, 2004. "Statistical Treatment Rules for Heterogeneous Populations," Econometrica, Econometric Society, vol. 72(4), pages 1221-1246, July.
    7. S. A. Murphy, 2003. "Optimal dynamic treatment regimes," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 65(2), pages 331-355, May.
    8. Susan Athey & Stefan Wager, 2021. "Policy Learning With Observational Data," Econometrica, Econometric Society, vol. 89(1), pages 133-161, January.
    9. Qizhao Chen & Morgane Austern & Vasilis Syrgkanis, 2023. "Inference on Optimal Dynamic Policies via Softmax Approximation," Papers 2303.04416, arXiv.org, revised Dec 2023.
    10. Heejung Bang & James M. Robins, 2005. "Doubly Robust Estimation in Missing Data and Causal Inference Models," Biometrics, The International Biometric Society, vol. 61(4), pages 962-973, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Justin Whitehouse & Morgane Austern & Vasilis Syrgkanis, 2025. "Inference on Optimal Policy Values and Other Irregular Functionals via Smoothing," Papers 2507.11780, arXiv.org.
    2. Nan Liu & Yanbo Liu & Yuya Sasaki & Yuanyuan Wan, 2025. "Nonparametric Uniform Inference in Binary Classification and Policy Values," Papers 2511.14700, arXiv.org, revised Dec 2025.
    3. Shosei Sakaguchi, 2021. "Estimation of Optimal Dynamic Treatment Assignment Rules under Policy Constraints," Papers 2106.05031, arXiv.org, revised Aug 2024.
    4. Henrika Langen & Martin Huber, 2023. "How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a coupon campaign," PLOS ONE, Public Library of Science, vol. 18(1), pages 1-37, January.
    5. Nora Bearth & Michael Lechner & Jana Mareckova & Fabian Muny, 2025. "Fairness-Aware and Interpretable Policy Learning," Papers 2509.12119, arXiv.org.
    6. Augustine Denteh & Helge Liebert, 2022. "Who Increases Emergency Department Use? New Insights from the Oregon Health Insurance Experiment," Papers 2201.07072, arXiv.org, revised Apr 2023.
    7. Achim Ahrens & Alessandra Stampi‐Bombelli & Selina Kurer & Dominik Hangartner, 2024. "Optimal multi‐action treatment allocation: A two‐phase field experiment to boost immigrant naturalization," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 39(7), pages 1379-1395, November.
    8. Davide Viviano & Jelena Bradic, 2020. "Fair Policy Targeting," Papers 2005.12395, arXiv.org, revised Jun 2022.
    9. Davide Viviano & Jess Rudder, 2020. "Policy design in experiments with unknown interference," Papers 2011.08174, arXiv.org, revised May 2024.
    10. Davide Viviano, 2019. "Policy Targeting under Network Interference," Papers 1906.10258, arXiv.org, revised Apr 2024.
    11. Hirano, Keisuke & Porter, Jack R., 2020. "Asymptotic analysis of statistical decision rules in econometrics," Handbook of Econometrics, in: Steven N. Durlauf & Lars Peter Hansen & James J. Heckman & Rosa L. Matzkin (ed.), Handbook of Econometrics, edition 1, volume 7, chapter 0, pages 283-354, Elsevier.
    12. Julia Hatamyar & Noemi Kreif, 2023. "Policy Learning with Rare Outcomes," Papers 2302.05260, arXiv.org, revised Oct 2023.
    13. David Glynn & John Giardina & Julia Hatamyar & Ankur Pandya & Marta Soares & Noemi Kreif, 2024. "Integrating decision modeling and machine learning to inform treatment stratification," Health Economics, John Wiley & Sons, Ltd., vol. 33(8), pages 1772-1792, August.
    14. Kyle Colangelo & Ying-Ying Lee, 2019. "Double debiased machine learning nonparametric inference with continuous treatments," CeMMAP working papers CWP72/19, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    15. Giovanni Cerulli & Francesco Caracciolo, 2025. "Risk-Adjusted Policy Learning and the Social Cost of Uncertainty: Theory and Evidence from CAP evaluation," Papers 2510.05007, arXiv.org.
    16. Manski, Charles F., 2023. "Probabilistic prediction for binary treatment choice: With focus on personalized medicine," Journal of Econometrics, Elsevier, vol. 234(2), pages 647-663.
    17. Masahiro Kato & Masaaki Imaizumi & Takuya Ishihara & Toru Kitagawa, 2023. "Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds," Papers 2302.02988, arXiv.org, revised Jul 2023.
    18. Anders Bredahl Kock & Martin Thyrsgaard, 2017. "Optimal sequential treatment allocation," Papers 1705.09952, arXiv.org, revised Aug 2018.
    19. Garbero, Alessandra & Sakos, Grayson & Cerulli, Giovanni, 2023. "Towards data-driven project design: Providing optimal treatment rules for development projects," Socio-Economic Planning Sciences, Elsevier, vol. 89(C).
    20. Yuchen Hu & Henry Zhu & Emma Brunskill & Stefan Wager, 2024. "Minimax-Regret Sample Selection in Randomized Experiments," Papers 2403.01386, arXiv.org, revised Jun 2024.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2510.19672. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.