RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback


METADATA ONLY
Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback and to consider human factors involved in providing feedback of different types. However, the systematic study of learning from diverse types of feedback is held back by limited standardized tooling available to researchers. To bridge this gap, we propose RLHF-Blender, a configurable, interactive interface for learning from human feedback. RLHF-Blender provides a modular experimentation framework and implementation that enables researchers to systematically investigate the properties and qualities of human feedback for reward learning. The system facilitates the exploration of various feedback types, including demonstrations, rankings, comparisons, and natural language instructions, as well as studies considering the impact of human factors on their effectiveness. We discuss a set of concrete research opportunities enabled by RLHF-Blender. More information is available at https://rlhfblender.info/.

Publication status

published

Editor

Book title

Interactive Learning with Implicit Human Feedback Workshop at ICML 2023

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

Interactive Learning from Implicit Human Feedback Workshop @ ICML 2023

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Reinforcement learning; Human feedback; Human-AI communication; Human-in-the-loop learning

Organisational unit

09822 - El-Assady, Mennatallah / El-Assady, Mennatallah check_circle

Notes

Poster presented on July 29, 2023.

Funding

Related publications and datasets

Is new version of: 10.48550/ARXIV.2308.04332