Blessing from human-AI interaction: super policy learning in confounded environments

Jiayi Wang, Zhengling Qi and Chengchun Shi

LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library

Abstract: As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this article, we introduce the paradigm of super policy learning that takes advantage of Human-AI interaction for data driven sequential decision making. This approach uses the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision maker (humans or AI). In the decision process with unmeasured confounding, the actions taken by past agents can offer valuable insights into undisclosed information. By including this information for the policy search in a novel and legitimate manner, the proposed super policy learning will yield a super-policy that is guaranteed to outperform both the standard optimal policy and the behavior one (e.g., past agents’ actions). We call this stronger oracle a blessing from human-AI interaction. Furthermore, to address the issue of unmeasured confounding in finding super-policies using the batch data, a number of nonparametric and causal identifications are established under the framework of proximal causal inference. Building upon on these novel identification results, we develop several super-policy learning algorithms and systematically study their theoretical properties such as finite-sample regret guarantee. Finally, we illustrate the effectiveness of our proposal through extensive simulations and real-world applications. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

Keywords: finite-sample regret bound; Human–AI interaction; nonparametric identification; policy learning; unmeasured confounding (search for similar items in EconPapers)
JEL-codes: C1 (search for similar items in EconPapers)
Pages: 14 pages
Date: 2026-03-16
References: Add references at CitEc
Citations:

Published in Journal of the American Statistical Association, 16, March, 2026. ISSN: 0162-1459

Downloads: (external link)
https://researchonline.lse.ac.uk/id/eprint/130007/ Open access version. (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ehl:lserod:130007

Access Statistics for this paper

More papers in LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library LSE Library Portugal Street London, WC2A 2HD, U.K.. Contact information at EDIRC.
Bibliographic data for series maintained by LSERO Manager ().