English

An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions

Machine Learning 2023-05-17 v1

Abstract

Apprenticeship learning (AL) is a process of inducing effective decision-making policies via observing and imitating experts' demonstrations. Most existing AL approaches, however, are not designed to cope with the evolving reward functions commonly found in human-centric tasks such as healthcare, where offline learning is required. In this paper, we propose an offline Time-aware Hierarchical EM Energy-based Sub-trajectory (THEMES) AL framework to tackle the evolving reward functions in such tasks. The effectiveness of THEMES is evaluated via a challenging task -- sepsis treatment. The experimental results demonstrate that THEMES can significantly outperform competitive state-of-the-art baselines.

Keywords

Cite

@article{arxiv.2305.09070,
  title  = {An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions},
  author = {Xi Yang and Ge Gao and Min Chi},
  journal= {arXiv preprint arXiv:2305.09070},
  year   = {2023}
}
R2 v1 2026-06-28T10:35:20.871Z