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.
@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}
}