Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework

TL;DR

This paper develops a comprehensive framework for understanding and categorizing human feedback in reinforcement learning, aiming to improve system design and identify research gaps.

Contribution

It introduces a taxonomy of human feedback types based on nine dimensions and identifies seven quality metrics affecting learning effectiveness.

Findings

Proposes a unified taxonomy for human feedback in RL.

Identifies key quality metrics influencing feedback effectiveness.

Highlights gaps and future directions in human-in-the-loop RL research.

Abstract

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our preferences, intentions, and knowledge to an RL agent. However, applications of human feedback in RL are often limited in scope and disregard human factors. In this work, we bridge the gap between machine learning and human-computer interaction efforts by developing a shared understanding of human feedback in interactive learning scenarios. We first introduce a taxonomy of feedback types for reward-based learning from human feedback based on nine key dimensions. Our taxonomy allows for unifying human-centered, interface-centered, and model-centered aspects. In addition, we identify seven quality metrics of human feedback influencing both the human ability to express feedback and the agent's ability to learn from the feedback. Based on the feedback taxonomy and quality criteria, we derive requirements and design choices for systems learning from human feedback. We relate these requirements and design choices to existing work in interactive machine learning. In the process, we identify gaps in existing work and future research opportunities. We call for interdisciplinary collaboration to harness the full potential of reinforcement learning with data-driven co-adaptive modeling and varied interaction mechanics.