{"type":"ScholarlyArticle","title":"Human-Centric Behavior-Aware Adaptive Off-Policy Selection","authors":[{"name":"Ge Gao","slug":"ge-gao","given":"Ge","family":"Gao","affiliation":"Stanford University"},{"name":"Aishwarya Mandyam","slug":"aishwarya-mandyam","given":"Aishwarya","family":"Mandyam","affiliation":"Stanford University"},{"name":"Joy He-Yueya","slug":"joy-he-yueya","given":"Joy","family":"He-Yueya","affiliation":"Stanford University"},{"name":"Min Chi","slug":"min-chi","given":"Min","family":"Chi","affiliation":"North Carolina State University"},{"name":"Emma Brunskill","slug":"emma-brunskill","given":"Emma","family":"Brunskill","affiliation":"Stanford University"}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2026/849","pdf":"https://ijcai.org/proceedings/2026/0849.pdf","markdown":"https://ijcai.org/proceedings/2026/849.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/849","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Human-Centred AI","track":"Human-Centred AI","number":849,"pages":{"first":7638,"last":7646},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}