Interactive Groupwise Comparison for Faster Reinforcement Learning from Human Feedback

Authors: J Kompatscher

Published: 2024

Publication: 2024 - aaltodoc.aalto.fi

Research paper: Interactive Groupwise Comparison for Faster Reinforcement Learning from Human Feedback

Research Area: Reinforcement Learning from Human Feedback (RLHF), Human-Computer Interaction (HCI), Machine Learning (ML)

Discipline: Computer Science

Citations: 1

DOI: https://urn.fi/URN:NBN:fi:aalto-202501271897