PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Jianhan, Wang, Jitao, Shi, Chengchun, Piette, John D., Zeng, Donglin, Wu, Zhenke
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909831369064448
author Zhang, Jianhan
Wang, Jitao
Shi, Chengchun
Piette, John D.
Zeng, Donglin
Wu, Zhenke
author_facet Zhang, Jianhan
Wang, Jitao
Shi, Chengchun
Piette, John D.
Zeng, Donglin
Wu, Zhenke
contents Reinforcement learning (RL) aims to learn and evaluate a sequential decision rule, often referred to as a "policy", that maximizes the population-level benefit in an environment across possibly infinitely many time steps. However, the sequential decisions made by an RL algorithm, while optimized to maximize overall population benefits, may disadvantage certain individuals who are in minority or socioeconomically disadvantaged groups. To address this problem, we introduce PyCFRL, a Python library for ensuring counterfactual fairness in offline RL. PyCFRL implements a novel data preprocessing algorithm for learning counterfactually fair RL policies from offline datasets and provides tools to evaluate the values and counterfactual unfairness levels of RL policies. We describe the high-level functionalities of PyCFRL and demonstrate one of its major use cases through a data example. The library is publicly available on PyPI and Github (https://github.com/JianhanZhang/PyCFRL), and detailed tutorials can be found in the PyCFRL documentation (https://pycfrl-documentation.netlify.app).
format Preprint
id arxiv_https___arxiv_org_abs_2510_06935
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing
Zhang, Jianhan
Wang, Jitao
Shi, Chengchun
Piette, John D.
Zeng, Donglin
Wu, Zhenke
Machine Learning
Reinforcement learning (RL) aims to learn and evaluate a sequential decision rule, often referred to as a "policy", that maximizes the population-level benefit in an environment across possibly infinitely many time steps. However, the sequential decisions made by an RL algorithm, while optimized to maximize overall population benefits, may disadvantage certain individuals who are in minority or socioeconomically disadvantaged groups. To address this problem, we introduce PyCFRL, a Python library for ensuring counterfactual fairness in offline RL. PyCFRL implements a novel data preprocessing algorithm for learning counterfactually fair RL policies from offline datasets and provides tools to evaluate the values and counterfactual unfairness levels of RL policies. We describe the high-level functionalities of PyCFRL and demonstrate one of its major use cases through a data example. The library is publicly available on PyPI and Github (https://github.com/JianhanZhang/PyCFRL), and detailed tutorials can be found in the PyCFRL documentation (https://pycfrl-documentation.netlify.app).
title PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing
topic Machine Learning
url https://arxiv.org/abs/2510.06935