arXiv Open Access 2023

Fairness in Preference-based Reinforcement Learning

Umer Siddique Abhinav Sinha Yongcan Cao

Lihat Sumber

Abstrak

In this paper, we address the issue of fairness in preference-based reinforcement learning (PbRL) in the presence of multiple objectives. The main objective is to design control policies that can optimize multiple objectives while treating each objective fairly. Toward this objective, we design a new fairness-induced preference-based reinforcement learning or FPbRL. The main idea of FPbRL is to learn vector reward functions associated with multiple objectives via new welfare-based preferences rather than reward-based preference in PbRL, coupled with policy learning via maximizing a generalized Gini welfare function. Finally, we provide experiment studies on three different environments to show that the proposed FPbRL approach can achieve both efficiency and equity for learning effective and fair policies.

Topik & Kata Kunci

cs.LG cs.AI cs.CY eess.SY

Penulis (3)

Umer Siddique

Abhinav Sinha

Yongcan Cao

Format Sitasi

APA MLA BibTeX

Siddique, U., Sinha, A., Cao, Y. (2023). Fairness in Preference-based Reinforcement Learning. https://arxiv.org/abs/2306.09995

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓