Behavior-Aware Off-Policy Selection in High-Stake Human-Centric Environments

ICLR 2026 Conference Submission22130 Authors

Keywords: Adaptive off-policy selection for high-stake human-centric environments, unobservability and personalization, intelligent tutoring, healthcare

Abstract: In many human-centric environments, such as education and healthcare, the unobservability of human underlying states has been recognized as a key obstacle for understanding individual needs, thus hindering out ability to provide personalized decision-making policies. Several reinforcement learning (RL)-related approaches have been used to facilitate sequential decision-making in these settings, including off-policy selection (OPS), which aids in safely evaluating and selecting optimal policies offline. However, existing OPS algorithms are unsuitable when both the state is unobserved and the setting requires a personalized policy. To address this challenge, we propose a behavior-aware adaptive policy selection framework (HBO) that first captures potentially unique characteristics of the state from human behaviors, and then estimates when and how to intervene with less uncertainty in a timely manner, with bounded error. HBO is evaluated over two real-world human-centric applications, intelligent tutoring and sepsis treatments, where it significantly enhanced participants' long-term course outcomes and survival rates. Broadly, our work enables improved policy personalization in high-stakes domains where extensive evaluation is not possible.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 22130