Offline Reinforcement Learning for Interval-Censored Data

ICLR 2026 Conference Submission15819 Authors

Keywords: Interval Censored Data; Survival Analysis; Reinforcement Learning

TL;DR: A reinforcement learning framework for multi-stage interval-censored data processing enables personalized behavioral recommendations, enhancing health management and longevity.

Abstract: This paper proposes a framework that applies reinforcement learning to multi-stage interval-censored data processing to develop an intelligent decision system capable of offering personalized behavioral recommendations based on observers' state and action variables. Interval-censored data is a common form of data encountered in practical data analysis, where observed results are only known to lie within certain intervals rather than exact values. This approach not only adapts to individual heterogeneity but also provides valuable decision support for personalized treatment. Experimental results demonstrate that this integrated approach effectively enhances individuals' longevity, providing a new method for personalized interventions and recommendations. This research is significant for the development of intelligent and personalized health management systems, offering valuable insights for future health sciences and intelligent decision systems.

Primary Area: reinforcement learning

Submission Number: 15819