Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

TL;DR

This paper presents QDHF, a novel method that learns diversity metrics from human feedback to improve diversity-driven optimization in complex, open-ended tasks, outperforming existing methods in various benchmarks.

Contribution

Introduces QDHF, a new approach that infers diversity metrics from human judgments, enhancing quality diversity algorithms for open-ended and generative tasks.

Findings

QDHF outperforms state-of-the-art methods in diversity discovery

QDHF matches the effectiveness of manually crafted metrics

QDHF significantly improves diversity in text-to-image generation

Abstract

Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for average human preferences, especially in generative tasks that demand diverse model responses. Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics. This paper introduces Quality Diversity through Human Feedback (QDHF), a novel approach that progressively infers diversity metrics from human judgments of similarity among solutions, thereby enhancing the applicability and effectiveness of QD algorithms in complex and open-ended domains. Empirical studies show that QDHF significantly outperforms state-of-the-art methods in automatic diversity discovery and matches the efficacy of QD with manually crafted diversity metrics on standard benchmarks in robotics and reinforcement learning. Notably, in open-ended generative tasks, QDHF substantially enhances the diversity of text-to-image generation from a diffusion model and is more favorably received in user studies. We conclude by analyzing QDHF's scalability, robustness, and quality of derived diversity metrics, emphasizing its strength in open-ended optimization tasks. Code and tutorials are available at https://liding.info/qdhf.