Saved in:
Bibliographic Details
Main Authors: White, Devin, Wu, Mingkang, Novoseller, Ellen, Lawhern, Vernon J., Waytowich, Nicholas, Cao, Yongcan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.16348
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917577297494016
author White, Devin
Wu, Mingkang
Novoseller, Ellen
Lawhern, Vernon J.
Waytowich, Nicholas
Cao, Yongcan
author_facet White, Devin
Wu, Mingkang
Novoseller, Ellen
Lawhern, Vernon J.
Waytowich, Nicholas
Cao, Yongcan
contents This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning. Different from the existing preference-based and ranking-based reinforcement learning paradigms, based on human relative preferences over sample pairs, the proposed rating-based reinforcement learning approach is based on human evaluation of individual trajectories without relative comparisons between sample pairs. The rating-based reinforcement learning approach builds on a new prediction model for human ratings and a novel multi-class loss function. We conduct several experimental studies based on synthetic ratings and real human ratings to evaluate the effectiveness and benefits of the new rating-based reinforcement learning approach.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16348
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Rating-based Reinforcement Learning
White, Devin
Wu, Mingkang
Novoseller, Ellen
Lawhern, Vernon J.
Waytowich, Nicholas
Cao, Yongcan
Machine Learning
Artificial Intelligence
Robotics
This paper develops a novel rating-based reinforcement learning approach that uses human ratings to obtain human guidance in reinforcement learning. Different from the existing preference-based and ranking-based reinforcement learning paradigms, based on human relative preferences over sample pairs, the proposed rating-based reinforcement learning approach is based on human evaluation of individual trajectories without relative comparisons between sample pairs. The rating-based reinforcement learning approach builds on a new prediction model for human ratings and a novel multi-class loss function. We conduct several experimental studies based on synthetic ratings and real human ratings to evaluate the effectiveness and benefits of the new rating-based reinforcement learning approach.
title Rating-based Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2307.16348