Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples
Abstract
Learning controllers with offline data in decision-making systems is an essential area of research due to its potential to reduce the risk of applications in real-world systems. However, in responsibility-sensitive settings such as healthcare, decision accountability is of paramount importance, yet has not been adequately addressed by the literature.This paper introduces the Accountable Offline Controller (AOC) that employs the offline dataset as the Decision Corpus and performs accountable control based on a tailored selection of examples, referred to as the Corpus Subset. AOC operates effectively in low-data scenarios, can be extended to the strictly offline imitation setting, and displays qualities of both conservation and adaptability.We assess AOC's performance in both simulated and real-world healthcare scenarios, emphasizing its capability to manage offline control tasks with high levels of performance while maintaining accountability.
Cite
Text
Sun et al. "Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples." Neural Information Processing Systems, 2023.Markdown
[Sun et al. "Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/sun2023neurips-accountability/)BibTeX
@inproceedings{sun2023neurips-accountability,
title = {{Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples}},
author = {Sun, Hao and Hüyük, Alihan and Jarrett, Daniel and van der Schaar, Mihaela},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/sun2023neurips-accountability/}
}