APReL: A Library for Active Preference-based Reward Learning Algorithms
Machine Learning
2022-01-05 v2 Artificial Intelligence
Robotics
Abstract
Reward learning is a fundamental problem in human-robot interaction to have robots that operate in alignment with what their human user wants. Many preference-based learning algorithms and active querying techniques have been proposed as a solution to this problem. In this paper, we present APReL, a library for active preference-based reward learning algorithms, which enable researchers and practitioners to experiment with the existing techniques and easily develop their own algorithms for various modules of the problem. APReL is available at https://github.com/Stanford-ILIAD/APReL.
Cite
@article{arxiv.2108.07259,
title = {APReL: A Library for Active Preference-based Reward Learning Algorithms},
author = {Erdem Bıyık and Aditi Talati and Dorsa Sadigh},
journal= {arXiv preprint arXiv:2108.07259},
year = {2022}
}
Comments
5 pages, 1 figures. Library is available at: https://github.com/Stanford-ILIAD/APReL