CHARM: Considering Human Attributes for Reinforcement Modeling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fang, Qidi, Yu, Hang, Fang, Shijie, Huang, Jindan, Chen, Qiuyu, Aronson, Reuben M., Short, Elaine S.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912792592777216
author Fang, Qidi
Yu, Hang
Fang, Shijie
Huang, Jindan
Chen, Qiuyu
Aronson, Reuben M.
Short, Elaine S.
author_facet Fang, Qidi
Yu, Hang
Fang, Shijie
Huang, Jindan
Chen, Qiuyu
Aronson, Reuben M.
Short, Elaine S.
contents Reinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior work acknowledged that human teachers' characteristics would affect human feedback patterns, there is little work that has closely investigated the actual effects. In this work, we designed an exploratory study investigating how human feedback patterns are associated with human characteristics. We conducted a public space study with two long horizon tasks and 46 participants. We found that feedback patterns are not only correlated with task statistics, such as rewards, but also correlated with participants' characteristics, especially robot experience and educational background. Additionally, we demonstrated that human feedback value can be more accurately predicted with human characteristics compared to only using task statistics. All human feedback and characteristics we collected, and codes for our data collection and predicting more accurate human feedback are available at https://github.com/AABL-Lab/CHARM
format Preprint
id arxiv_https___arxiv_org_abs_2506_13079
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CHARM: Considering Human Attributes for Reinforcement Modeling
Fang, Qidi
Yu, Hang
Fang, Shijie
Huang, Jindan
Chen, Qiuyu
Aronson, Reuben M.
Short, Elaine S.
Robotics
Human-Computer Interaction
Reinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior work acknowledged that human teachers' characteristics would affect human feedback patterns, there is little work that has closely investigated the actual effects. In this work, we designed an exploratory study investigating how human feedback patterns are associated with human characteristics. We conducted a public space study with two long horizon tasks and 46 participants. We found that feedback patterns are not only correlated with task statistics, such as rewards, but also correlated with participants' characteristics, especially robot experience and educational background. Additionally, we demonstrated that human feedback value can be more accurately predicted with human characteristics compared to only using task statistics. All human feedback and characteristics we collected, and codes for our data collection and predicting more accurate human feedback are available at https://github.com/AABL-Lab/CHARM
title CHARM: Considering Human Attributes for Reinforcement Modeling
topic Robotics
Human-Computer Interaction
url https://arxiv.org/abs/2506.13079