Human-Centric Behavior-Aware Adaptive Off-Policy Selection
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Human-Centred AI. Pages 7638-7646.
© 2026 International Joint Conferences on Artificial Intelligence
Keywords
- Human-Centred AI: Agent-based and Multi-agent Systems
- Human-Centred AI: Humans and AI
- Human-Centred AI: Uncertainty in AI
- Human-Centred AI: Multidisciplinary Topics and Applications
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 our 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.
@inproceedings{ijcai2026p849,
title = {Human-Centric Behavior-Aware Adaptive Off-Policy Selection},
author = {Gao, Ge and Mandyam, Aishwarya and He-Yueya, Joy and Chi, Min and Brunskill, Emma},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {7638--7646},
year = {2026},
month = {8},
note = {Human-Centred AI},
url = {https://ijcai.org/proceedings/2026/849},
}
TY - CPAPER TI - Human-Centric Behavior-Aware Adaptive Off-Policy Selection AU - Gao, Ge AU - Mandyam, Aishwarya AU - He-Yueya, Joy AU - Chi, Min AU - Brunskill, Emma T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 7638 EP - 7646 UR - https://ijcai.org/proceedings/2026/849 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: